Comparison of GARCH and Data Science Models in Financial Times Series Forecasting: An analysis for the financial market volatility in the banking and automobile industry.

Contents

1. Libraries
2. Data preparation
3. EDA
4. Building Models GARCH models

• ARCH
• GARCH model
• GARCH-t model
• EGARCH model

Data Science models

• LSTM
• Random Forest

1. Models comparison

Libraries

import pandas as pd
import numpy as np
import seaborn as sns
import missingno as msno
import yfinance as yf
import matplotlib.pyplot as plt
import math
import statsmodels.api as sm
from scipy.stats import norm
import scipy.optimize as opt
import datetime
import time
from sklearn.metrics import mean_squared_error as mse
from arch import arch_model
from statsmodels.tsa.stattools import ARMA
from statsmodels.tsa.arima_model import ARIMA
from time import time
import sys
pd.options.display.max_rows = 10
import datetime
from matplotlib.pyplot import figure
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
from tensorflow.keras import layers
from numpy import asarray
from pandas import DataFrame
from pandas import concat
from sklearn.metrics import mean_absolute_error
from sklearn.ensemble import RandomForestRegressor
from matplotlib import pyplot
from sklearn.metrics import mean_squared_error
from math import sqrt
from tabulate import tabulate
import statsmodels.tsa.api as tsa
import matplotlib.cm as cm
from matplotlib.pyplot import figure
import warnings
warnings.filterwarnings("ignore")

Data preparation

Import Data

We use data from four international stock markets, including two different industries (Banking and Automotive) retrieved from YahooFinance from the period 2000-01-01 to 2020-12-31.

#Let's read the data for the chosen period (2000-01-01 --> 2020-12-31)
Tickers = ["DBK.DE", "BAC", "BMW.DE", "F"]
df= yf.download(Tickers, start = "2000-01-01", end = "2020-12-31") ['Close']
df.columns = df.columns.str.lower().str.replace(' ', '_')
df

[*********************100%***********************]  4 of 4 completed

	bac	bmw.de	dbk.de	f
Date
1999-12-31	25.093750	NaN	NaN	29.297592
2000-01-03	24.218750	29.490000	65.045204	28.782394
2000-01-04	22.781250	28.299999	61.775078	27.820692
2000-01-05	23.031250	27.740000	60.975021	27.923731
2000-01-06	25.000000	27.650000	64.082031	27.958078
...	...	...	...	...
2020-12-23	30.049999	73.379997	8.983000	8.990000
2020-12-24	29.959999	NaN	NaN	8.860000
2020-12-28	30.129999	73.489998	9.218000	8.890000
2020-12-29	30.010000	73.160004	8.944000	8.820000
2020-12-30	29.980000	72.230003	8.949000	8.860000

5438 rows × 4 columns

Daily returns

#Let's calculate the "Daily log returns" 
df[['Ret_BAC', 'Ret_BMW', 'Ret_DBK', 'Ret_F']]=np.log(df[['bac','bmw.de', 'dbk.de', 'f']]).diff()
df = df.dropna() #Deleting missing values

#Converting the table as a Data Frame to be more practical 
df = pd.DataFrame(df)

#Keeping only the retuns columns 
df_RET = df[['Ret_BAC', 'Ret_BMW', 'Ret_DBK', 'Ret_F']]
df_RET

	Ret_BAC	Ret_BMW	Ret_DBK	Ret_F
Date
2000-01-04	-0.061189	-0.041189	-0.051582	-0.033984
2000-01-05	0.010914	-0.019986	-0.013036	0.003697
2000-01-06	0.082024	-0.003250	0.049700	0.001229
2000-01-07	-0.026601	-0.001810	0.029853	0.071120
2000-01-10	-0.035275	0.039081	-0.026102	-0.018476
...	...	...	...	...
2020-12-21	0.036642	-0.030380	-0.045192	-0.002237
2020-12-22	-0.017982	0.001805	0.017799	-0.015802
2020-12-23	0.028352	0.017597	0.022174	0.022498
2020-12-29	-0.003991	-0.004500	-0.030175	-0.007905
2020-12-30	-0.001000	-0.012793	0.000559	0.004525

5008 rows × 4 columns

Realized Volatility

#Calculating the "Realized Volatility" using the close-to-close method
df_Vol = df_RET.std()* 252 ** 0.5 #252 are the trading days
df_Vol

Ret_BAC    0.457025
Ret_BMW    0.334252
Ret_DBK    0.411080
Ret_F      0.419874
dtype: float64

Data per company

# Prepare the Data frame for each company

## DBK
DBK_RET = df[['Ret_DBK']]*100 #*100 because the GARCH fitting process has better convergence if we express the returns as percents

##BAC
BAC_RET = df[['Ret_BAC']] * 100

##BMW
BMW_RET = df[['Ret_BMW']] * 100

##Ford
F_RET = df[['Ret_F']] * 100

EDA

Plot Daily returns / historical price (per company)

DBK

# Plotting DBK Price
fig = plt.figure()
plt.figure(figsize=(20, 7))
plt.plot(df[["dbk.de"]], label = ('DBK historical prices'))
plt.legend(loc='upper right')
plt.title('DBK: historical prices', fontsize=16)
plt.show()

# Plotting DBK Returns
fig = plt.figure()
plt.figure(figsize=(20, 7))
plt.plot(df[["Ret_DBK"]], label = ('BAC historical prices'))
plt.legend(loc='upper right')
plt.title('DBK: Daily returns', fontsize=16)
plt.show()

<Figure size 432x288 with 0 Axes>

<Figure size 432x288 with 0 Axes>

• We can see that DBK prices have fluctuated significantly. Indeed, the financial crisis of 2003 (new market) which arrived in Germany strongly impacted the prices of DBK. It was not until about 2004 that prices began to rise (with some decreases), only to fall drastically again due to the global financial crisis of 2007-2008. Then, prices rose slightly but started to fall again due to a third crisis between 2011 and 2012 (European debt crisis). Prices continued to fall throughout the period shown on the chart. And we can justify the sharp decline in prices in 2020 by the COVID-19 health crisis that heavily impacted the global banking sector.
• We can confirm this analysis by the high volatility of returns on the second graph (daily returns) during the periods 2003-2004, 2007-2010, 2011- 2013 and 2016-2020.

BAC

# Plotting BAC Price
fig = plt.figure()
plt.figure(figsize=(20, 7))
plt.plot(df[["bac"]], label = ('BAC historical prices'))
plt.legend(loc='upper right')
plt.title('BAC: historical prices', fontsize=16)
plt.show()

# Plotting BAC Returns
fig = plt.figure()
plt.figure(figsize=(20, 7))
plt.plot(df[["Ret_BAC"]], label = ('BAC historical prices'))
plt.legend(loc='upper right')
plt.title('BAC: Daily returns', fontsize=16)
plt.show()

<Figure size 432x288 with 0 Axes>

<Figure size 432x288 with 0 Axes>

We can apply the same analysis to the BAC case. However, in the United States, we can judge that the effects of the 2003 financial crisis were minimal. Indeed, we can see that prices continued to rise during this period. The same is true for the 2011-2012 period. The two major events where we notice a strong decrease in prices, as well as a high level of volatility (BAC: Daily returns) are the global crisis of 2007 and the COVID-19 health crisis.

BMW

# Plotting BMW Price
fig = plt.figure()
plt.figure(figsize=(20, 7))
plt.plot(df[["bmw.de"]], label = ('BMW historical prices'))
plt.legend(loc='upper right')
plt.title('BMW: historical prices', fontsize=16)
plt.show()

# Plotting BMW Returns
fig = plt.figure()
plt.figure(figsize=(20, 7))
plt.plot(df[["Ret_BMW"]], label = ('BMW historical prices'))
plt.legend(loc='upper right')
plt.title('BMW: Daily returns', fontsize=16)
plt.show()

<Figure size 432x288 with 0 Axes>

<Figure size 432x288 with 0 Axes>

• In the case of BMW, prices were impacted by the crises of 2003 and 2008 to reach their minimum in 2009-2010. Then, despite the crisis of 2011- 2012, we can say that the prices have increased despite some decreases until reaching a maximum just before 2016, to begin to decline again. And we can clearly see the effect of the COVID-19 crisis, however, the prices started to increase again after 2020.
• We can clearly see the high volatility (BMW: Daily returns) of returns during the same periods mentioned above.

FORD

# Plotting FORD Price
fig = plt.figure()
plt.figure(figsize=(20, 7))
plt.plot(df[["f"]], label = ('FORD historical prices'))
plt.legend(loc='upper right')
plt.title('FORD: historical prices', fontsize=16)
plt.show()

# Plotting FORD Returns
fig = plt.figure()
plt.figure(figsize=(20, 7))
plt.plot(df[["Ret_F"]], label = ('FORD historical prices'))
plt.legend(loc='upper right')
plt.title('FORD: Daily returns', fontsize=16)
plt.show()

<Figure size 432x288 with 0 Axes>

<Figure size 432x288 with 0 Axes>

Ford's prices dropped drastically from 2002-2003 until they reached their minimum in 2009 due to the global crisis in 2007. After this period, the prices started to increase and then decreased in 2011, which means that the company was affected by the 2011-2012 crisis that occurred in Germany. Thereafter, prices continued to decline. this analysis is confirmed by the high volatility of returns during these periods.

Plotting Daily returns (Per Industry)

DBK vs BAC

fig = plt.figure()
plt.figure(figsize=(20, 7))
plt.plot(df_RET[["Ret_BAC","Ret_DBK"]], label = ('BAC daily returns', 'DBK daily returns'))
plt.legend(loc='upper right')
plt.title('Daily Returns: Banking industry', fontsize=16)
plt.show()

<Figure size 432x288 with 0 Axes>

We can see that DBK was affected by the 2003 crisis, unlike LAC. However, the financial crisis of 2008 had a much greater impact on BAC than on DBK.

BMW vs FORD

fig = plt.figure()
plt.figure(figsize=(20, 7))
plt.plot(df_RET[["Ret_BMW","Ret_F"]], label = ('BMW daily returns', 'FORD daily returns'))
plt.legend(loc='upper right')
plt.title('Daily Returns: Car manufacturers', fontsize=16)
plt.show()

<Figure size 432x288 with 0 Axes>

We can note that the level of volatility of Ford is higher than that of BMW. We can explain this by the fact that Ford was more affected by the crises that took place during the period studied.

Building Models

GARCH models

ARCH

Deutsche Bank AG

# Specify ARCH model assumptions
ARCH_DBK = arch_model(DBK_RET, p = 1, q = 0, vol = 'ARCH', dist = 'normal')

# Fit the model
ARCH_result_DBK = ARCH_DBK.fit(update_freq=5, disp="off")

# Get model estimated volatility
ARCH_vol_DBK = ARCH_result_DBK.conditional_volatility

# Forecasting
Prediction_DBK = ARCH_result_DBK.forecast(horizon = 1, start = '2020-12-14')
Forecast_ARCH_DBK = Prediction_DBK
Forecast_ARCH_DBK

print(ARCH_result_DBK.summary())

                      Constant Mean - ARCH Model Results                      
==============================================================================
Dep. Variable:                Ret_DBK   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                       ARCH   Log-Likelihood:               -11629.2
Distribution:                  Normal   AIC:                           23264.3
Method:            Maximum Likelihood   BIC:                           23283.9
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:07   Df Model:                            1
                                Mean Model                                
==========================================================================
                 coef    std err          t      P>|t|    95.0% Conf. Int.
--------------------------------------------------------------------------
mu            -0.0319  3.729e-02     -0.856      0.392 [ -0.105,4.116e-02]
                            Volatility Model                            
========================================================================
                 coef    std err          t      P>|t|  95.0% Conf. Int.
------------------------------------------------------------------------
omega          4.7845      0.265     18.042  9.083e-73 [  4.265,  5.304]
alpha[1]       0.3039  4.624e-02      6.573  4.936e-11 [  0.213,  0.395]
========================================================================

Covariance estimator: robust

# Calculate the RMSE 

a = 90
DBK_90 = DBK_RET.iloc[-a:].index # We are going to use it for our plot (Plot 90 days of real observations)
b = 10 # 10 days of forecasting
DBK_10 = DBK_RET.iloc[-b:].index 

rmse_arch = np.sqrt(mse(DBK_RET[-b:] / 100,
                        np.sqrt(Forecast_ARCH_DBK\
                                .variance.iloc[-len(DBK_10):]
                                / 100)))
print('The RMSE value of ARCH model (DBK): {:.4f}'.format(rmse_arch))

The RMSE value of ARCH model (DBK): 0.2504

Bank of America Corp

# Specify GARCH model assumptions
ARCH_BAC = arch_model(BAC_RET, p = 1, q = 0, vol = 'ARCH', dist = 'normal')

# Fit the model
ARCH_result_BAC = ARCH_BAC.fit(update_freq=5, disp="off")

# Get model estimated volatility
ARCH_vol_BAC = ARCH_result_BAC.conditional_volatility

# Forecasting
Prediction_BAC = ARCH_result_BAC.forecast(horizon = 1, start = '2020-12-14')
Forecast_ARCH_BAC = Prediction_BAC
Forecast_ARCH_BAC
print(ARCH_result_BAC.summary())

                      Constant Mean - ARCH Model Results                      
==============================================================================
Dep. Variable:                Ret_BAC   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                       ARCH   Log-Likelihood:               -11212.0
Distribution:                  Normal   AIC:                           22429.9
Method:            Maximum Likelihood   BIC:                           22449.5
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:08   Df Model:                            1
                                  Mean Model                                  
==============================================================================
                  coef    std err          t      P>|t|       95.0% Conf. Int.
------------------------------------------------------------------------------
mu         -5.3240e-04  4.322e-02 -1.232e-02      0.990 [-8.523e-02,8.417e-02]
                            Volatility Model                            
========================================================================
                 coef    std err          t      P>|t|  95.0% Conf. Int.
------------------------------------------------------------------------
omega          2.6180      0.185     14.135  2.315e-45 [  2.255,  2.981]
alpha[1]       1.0000      0.140      7.163  7.886e-13 [  0.726,  1.274]
========================================================================

Covariance estimator: robust

# Calculate the RMSE

c = 90
BAC_90 = BAC_RET.iloc[-a:].index 
d = 10
BAC_10 = BAC_RET.iloc[-b:].index 

rmse_arch = np.sqrt(mse(BAC_RET[-d:] / 100,
                        np.sqrt(Forecast_ARCH_BAC\
                                .variance.iloc[-len(BAC_10):]
                                / 100)))
print('The RMSE value of ARCH model (BAC): {:.4f}'.format(rmse_arch))

The RMSE value of ARCH model (BAC): 0.2273

# Ploting Returns/Conditional Variance

## DBK
figure(figsize=(20, 6), dpi=100)
plt.plot(ARCH_vol_DBK, color = 'red', label = 'Conditional Variance')
plt.plot(DBK_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('ARCH: Returns/Conditional Variance (DBK)', fontsize=16)
plt.show()

## BAC
figure(figsize=(20, 6), dpi=100)
plt.plot(ARCH_vol_BAC, color = 'red', label = 'Conditional Variance')
plt.plot(BAC_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('ARCH: Returns/Conditional Variance (BAC)', fontsize=16)
plt.show()

# Ploting Actual Returns/Predicted Returns 

## DBK
plt.figure(figsize=(20, 7))
plt.plot(DBK_RET.iloc[-len(DBK_90):] / 100, label='Actual Returns')
plt.plot(Forecast_ARCH_DBK.variance.iloc[-len(DBK_10):] / 100,
        label='Predicted Returns')
plt.title('ARCH: Actual Returns/Predicted Returns (DBK)', fontsize=16)
plt.legend()
plt.show()

## BAC
plt.figure(figsize=(20, 7))
plt.plot(BAC_RET.iloc[-len(BAC_90):] / 100, label='Actual Returns')
plt.plot(Forecast_ARCH_BAC.variance.iloc[-len(BAC_10):] / 100,
        label='Predicted Returns')
plt.title('ARCH: Actual Returns/Predicted Returns (BAC)', fontsize=16)
plt.legend()
plt.show()

BMW

# Specify ARCH model assumptions
ARCH_BMW = arch_model(BMW_RET, p = 1, q = 0, vol = 'ARCH', dist = 'normal')

# Fit the model
ARCH_result_BMW = ARCH_BMW.fit(update_freq=5, disp="off")

# Get model estimated volatility
ARCH_vol_BMW = ARCH_result_BMW.conditional_volatility

# Forecasting
Prediction_BMW = ARCH_result_BMW.forecast(horizon = 1, start = '2020-12-14')
Forecast_ARCH_BMW = Prediction_BMW
Forecast_ARCH_BMW

print(ARCH_result_BMW.summary())

                      Constant Mean - ARCH Model Results                      
==============================================================================
Dep. Variable:                Ret_BMW   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                       ARCH   Log-Likelihood:               -10687.0
Distribution:                  Normal   AIC:                           21380.0
Method:            Maximum Likelihood   BIC:                           21399.5
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:09   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu         6.5426e-03  2.916e-02      0.224      0.822 [-5.060e-02,6.369e-02]
                            Volatility Model                            
========================================================================
                 coef    std err          t      P>|t|  95.0% Conf. Int.
------------------------------------------------------------------------
omega          3.3410      0.170     19.670  3.863e-86 [  3.008,  3.674]
alpha[1]       0.2752  4.378e-02      6.286  3.265e-10 [  0.189,  0.361]
========================================================================

Covariance estimator: robust

# Calculate the RMSE

e = 90
BMW_90 = BMW_RET.iloc[-e:].index 
f = 10
BMW_10 = BMW_RET.iloc[-f:].index 

rmse_arch = np.sqrt(mse(BMW_RET[-f:] / 100,
                        np.sqrt(Forecast_ARCH_BMW\
                                .variance.iloc[-len(BMW_10):]
                                / 100)))
print('The RMSE value of ARCH model (BMW): {:.4f}'.format(rmse_arch))

The RMSE value of ARCH model (BMW): 0.2005

Ford

# Specify ARCH model assumptions
ARCH_F = arch_model(F_RET, p = 1, q = 0, vol = 'ARCH', dist = 'normal')

# Fit the model
ARCH_result_F = ARCH_F.fit(update_freq=5, disp="off")

# Get model estimated volatility
ARCH_vol_F = ARCH_result_F.conditional_volatility

# Forecasting
Prediction_F = ARCH_result_F.forecast(horizon = 1, start = '2020-12-14')
Forecast_ARCH_F = Prediction_F
Forecast_ARCH_F

print(ARCH_result_F.summary())

                      Constant Mean - ARCH Model Results                      
==============================================================================
Dep. Variable:                  Ret_F   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                       ARCH   Log-Likelihood:               -11464.9
Distribution:                  Normal   AIC:                           22935.8
Method:            Maximum Likelihood   BIC:                           22955.4
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:09   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu            -0.0140  3.852e-02     -0.362      0.717 [-8.945e-02,6.155e-02]
                            Volatility Model                            
========================================================================
                 coef    std err          t      P>|t|  95.0% Conf. Int.
------------------------------------------------------------------------
omega          3.7447      0.225     16.639  3.644e-62 [  3.304,  4.186]
alpha[1]       0.5683  8.532e-02      6.660  2.730e-11 [  0.401,  0.736]
========================================================================

Covariance estimator: robust

# Calculate the RMSE

g = 90
F_90 = F_RET.iloc[-g:].index 
h = 10
F_10 = F_RET.iloc[-h:].index 

rmse_arch = np.sqrt(mse(F_RET[-h:] / 100,
                        np.sqrt(Forecast_ARCH_F\
                                .variance.iloc[-len(F_10):]
                                / 100)))
print('The RMSE value of ARCH model (Ford): {:.4f}'.format(rmse_arch))

The RMSE value of ARCH model (Ford): 0.2219

# Ploting Returns/Conditional Variance

## BMW
figure(figsize=(20, 6), dpi=100)
plt.plot(ARCH_vol_BMW, color = 'red', label = 'Conditional Variance')
plt.plot(BMW_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('ARCH: Returns/Conditional Variance (BMW)', fontsize=16)
plt.show()

## Ford
figure(figsize=(20, 6), dpi=100)
plt.plot(ARCH_vol_F, color = 'red', label = 'Conditional Variance')
plt.plot(F_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('ARCH: Returns/Conditional Variance (FORD)', fontsize=16)
plt.show()

# Ploting Actual Returns/Predicted Returns 

## BMW
plt.figure(figsize=(20, 7))
plt.plot(BMW_RET.iloc[-len(BMW_90):] / 100, label='Actual Returns')
plt.plot(Forecast_ARCH_BMW.variance.iloc[-len(BMW_10):] / 100,
        label='Predicted Returns')
plt.title('ARCH: Actual Returns/Predicted Returns (BMW)', fontsize=16)
plt.legend()
plt.show()

## FORD
plt.figure(figsize=(20, 7))
plt.plot(F_RET.iloc[-len(F_90):] / 100, label='Actual Returns')
plt.plot(Forecast_ARCH_F.variance.iloc[-len(F_10):] / 100,
        label='Predicted Returns')
plt.title('ARCH: Actual Returns/Predicted Returns (FORD)', fontsize=16)
plt.legend()
plt.show()

GARCH model

Deutsche Bank AG

# Specify GARCH model assumptions
GARCH_DBK = arch_model(DBK_RET, p = 1, q = 1, mean = 'constant', vol = 'GARCH', dist = 'normal')

# Fit the model
GARCH_result_DBK = GARCH_DBK.fit(update_freq=5, disp="off")

# Get model estimated volatility
GARCH_vol_DBK = GARCH_result_DBK.conditional_volatility

# Forecasting
Prediction_GARCH_DBK = GARCH_result_DBK.forecast(horizon = 1, start = '2020-12-14')
Forecast_GARCH_DBK = Prediction_GARCH_DBK
Forecast_GARCH_DBK

print(GARCH_result_DBK.summary())

                     Constant Mean - GARCH Model Results                      
==============================================================================
Dep. Variable:                Ret_DBK   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                      GARCH   Log-Likelihood:               -10944.0
Distribution:                  Normal   AIC:                           21896.0
Method:            Maximum Likelihood   BIC:                           21922.0
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:10   Df Model:                            1
                                  Mean Model                                  
==============================================================================
                  coef    std err          t      P>|t|       95.0% Conf. Int.
------------------------------------------------------------------------------
mu         -2.9844e-03  2.648e-02     -0.113      0.910 [-5.489e-02,4.892e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0361  1.302e-02      2.775  5.525e-03 [1.061e-02,6.163e-02]
alpha[1]       0.0687  1.056e-02      6.502  7.920e-11 [4.797e-02,8.937e-02]
beta[1]        0.9273  1.106e-02     83.826      0.000     [  0.906,  0.949]
============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(DBK_RET[-b:] / 100,
                        np.sqrt(Forecast_GARCH_DBK\
                                .variance.iloc[-len(DBK_10):]
                                / 100)))
print('The RMSE value of GARCH model (DBK): {:.4f}'.format(rmse_arch))

The RMSE value of GARCH model (DBK): 0.2076

Bank of America Corp

# Specify GARCH model assumptions
GARCH_BAC = arch_model(BAC_RET, p = 1, q = 1, mean = 'constant', vol = 'GARCH', dist = 'normal')

# Fit the model
GARCH_result_BAC = GARCH_BAC.fit(update_freq=5, disp="off")

# Get model estimated volatility
GARCH_vol_BAC = GARCH_result_BAC.conditional_volatility

# Forecasting
Prediction_GARCH_BAC = GARCH_result_BAC.forecast(horizon = 1, start = '2020-12-14')
Forecast_GARCH_BAC = Prediction_GARCH_BAC
Forecast_GARCH_BAC

print(GARCH_result_BAC.summary())

                     Constant Mean - GARCH Model Results                      
==============================================================================
Dep. Variable:                Ret_BAC   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                      GARCH   Log-Likelihood:               -10148.2
Distribution:                  Normal   AIC:                           20304.4
Method:            Maximum Likelihood   BIC:                           20330.5
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:11   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu             0.0349  2.215e-02      1.577      0.115 [-8.477e-03,7.834e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0473  2.374e-02      1.993  4.627e-02 [7.834e-04,9.383e-02]
alpha[1]       0.0941  2.359e-02      3.989  6.649e-05   [4.786e-02,  0.140]
beta[1]        0.8983  2.488e-02     36.103 2.008e-285     [  0.849,  0.947]
============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(BAC_RET[-d:] / 100,
                        np.sqrt(Forecast_GARCH_BAC\
                                .variance.iloc[-len(BAC_10):]
                                / 100)))
print('The RMSE value of GARCH model (BAC): {:.4f}'.format(rmse_arch))

The RMSE value of GARCH model (BAC): 0.1982

# Ploting Returns/Conditional Variance

## DBK
figure(figsize=(20, 6), dpi=100)
plt.plot(GARCH_vol_DBK, color = 'red', label = 'Conditional Variance')
plt.plot(DBK_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GARCH: Returns/Conditional Variance (DBK)', fontsize=16)
plt.show()

## BAC
figure(figsize=(20, 6), dpi=100)
plt.plot(GARCH_vol_BAC, color = 'red', label = 'Conditional Variance')
plt.plot(BAC_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GARCH: Returns/Conditional Variance (BAC)', fontsize=16)
plt.show()

# Ploting Actual Returns/Predicted Returns 

## DBK
plt.figure(figsize=(20, 6))
plt.plot(DBK_RET.iloc[-len(DBK_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GARCH_DBK.variance.iloc[-len(DBK_10):] / 100,
        label='Predicted Returns')
plt.title('GARCH: Actual Returns/Predicted Returns (DBK)', fontsize=16)
plt.legend()
plt.show()

## BAC
plt.figure(figsize=(20, 6))
plt.plot(BAC_RET.iloc[-len(BAC_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GARCH_BAC.variance.iloc[-len(BAC_10):] / 100,
        label='Predicted Returns')
plt.title('GARCH: Actual Returns/Predicted Returns (BAC)', fontsize=16)
plt.legend()
plt.show()

BMW

# Specify GARCH model assumptions
GARCH_BMW = arch_model(BMW_RET, p = 1, q = 1, mean = 'constant', vol = 'GARCH', dist = 'normal')

# Fit the model
GARCH_result_BMW = GARCH_BMW.fit(update_freq=5, disp="off")

# Get model estimated volatility
GARCH_vol_BMW = GARCH_result_BMW.conditional_volatility

# Forecasting
Prediction_GARCH_BMW = GARCH_result_BMW.forecast(horizon = 1, start = '2020-12-14')
Forecast_GARCH_BMW = Prediction_GARCH_BMW
Forecast_GARCH_BMW

print(GARCH_result_BMW.summary())

                     Constant Mean - GARCH Model Results                      
==============================================================================
Dep. Variable:                Ret_BMW   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                      GARCH   Log-Likelihood:               -10114.2
Distribution:                  Normal   AIC:                           20236.4
Method:            Maximum Likelihood   BIC:                           20262.4
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:12   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu             0.0345  2.325e-02      1.485      0.138 [-1.105e-02,8.007e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0314  1.083e-02      2.898  3.755e-03 [1.016e-02,5.263e-02]
alpha[1]       0.0609  1.005e-02      6.054  1.415e-09 [4.116e-02,8.057e-02]
beta[1]        0.9324  1.101e-02     84.709      0.000     [  0.911,  0.954]
============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(BMW_RET[-f:] / 100,
                        np.sqrt(Forecast_GARCH_BMW\
                                .variance.iloc[-len(BMW_10):]
                                / 100)))
print('The RMSE value of GARCH model (BMW): {:.4f}'.format(rmse_arch))

The RMSE value of GARCH model (BMW): 0.1828

Ford

# Specify GARCH model assumptions
GARCH_F = arch_model(F_RET, p = 1, q = 1, mean = 'constant', vol = 'GARCH', dist = 'normal')

# Fit the model
GARCH_result_F = GARCH_F.fit(update_freq=5, disp="off")

# Get model estimated volatility
GARCH_vol_F = GARCH_result_F.conditional_volatility

# Forecasting
Prediction_GARCH_F = GARCH_result_F.forecast(horizon = 1, start = '2020-12-14')
Forecast_GARCH_F = Prediction_GARCH_F
Forecast_GARCH_F

print(GARCH_result_F.summary())

                     Constant Mean - GARCH Model Results                      
==============================================================================
Dep. Variable:                  Ret_F   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                      GARCH   Log-Likelihood:               -10945.9
Distribution:                  Normal   AIC:                           21899.8
Method:            Maximum Likelihood   BIC:                           21925.9
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:12   Df Model:                            1
                                Mean Model                                
==========================================================================
                 coef    std err          t      P>|t|    95.0% Conf. Int.
--------------------------------------------------------------------------
mu            -0.0453  2.828e-02     -1.602      0.109 [ -0.101,1.013e-02]
                              Volatility Model                             
===========================================================================
                 coef    std err          t      P>|t|     95.0% Conf. Int.
---------------------------------------------------------------------------
omega          0.0704  3.651e-02      1.929  5.377e-02 [-1.143e-03,  0.142]
alpha[1]       0.0664  2.037e-02      3.261  1.110e-03  [2.650e-02,  0.106]
beta[1]        0.9221  2.491e-02     37.013 7.028e-300    [  0.873,  0.971]
===========================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(F_RET[-h:] / 100,
                        np.sqrt(Forecast_GARCH_F\
                                .variance.iloc[-len(F_10):]
                                / 100)))
print('The RMSE value of GARCH model (Ford): {:.4f}'.format(rmse_arch))

The RMSE value of GARCH model (Ford): 0.2174

# Ploting Returns/Conditional Variance

## BMW
figure(figsize=(20, 6), dpi=100)
plt.plot(GARCH_vol_BMW, color = 'red', label = 'Conditional Variance')
plt.plot(BMW_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GARCH: Returns/Conditional Variance (BMW)', fontsize=16)
plt.show()

## Ford
figure(figsize=(20, 6), dpi=100)
plt.plot(GARCH_vol_F, color = 'red', label = 'Conditional Variance')
plt.plot(F_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GARCH: Returns/Conditional Variance (FORD)', fontsize=16)
plt.show()

# Ploting Actual Returns/Predicted Returns 

## BMW
plt.figure(figsize=(20, 6))
plt.plot(BMW_RET.iloc[-len(BMW_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GARCH_BMW.variance.iloc[-len(BMW_10):] / 100,
        label='Predicted Returns')
plt.title('GARCH: Actual Returns/Predicted Returns (BMW)', fontsize=16)
plt.legend()
plt.show()

## Ford
plt.figure(figsize=(20, 6))
plt.plot(F_RET.iloc[-len(F_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GARCH_F.variance.iloc[-len(F_10):] / 100,
        label='Predicted Returns')
plt.title('GARCH: Actual Returns/Predicted Returns (FORD)', fontsize=16)
plt.legend()
plt.show()

GARCH-t model

Deutsche Bank AG

# Specify GARCH model assumptions
GARCHt_DBK = arch_model(DBK_RET, p = 1,o=0, q = 1, vol = 'GARCH', dist = "StudentsT")

# Fit the model
GARCHt_result_DBK = GARCHt_DBK.fit(update_freq=5, disp="off")

# Get model estimated volatility
GARCHt_vol_DBK = GARCHt_result_DBK.conditional_volatility

# Forecasting
Prediction_GARCHt_DBK = GARCHt_result_DBK.forecast(horizon = 1, start = '2020-12-14')
Forecast_GARCHt_DBK = Prediction_GARCHt_DBK
Forecast_GARCHt_DBK

print(GARCHt_result_DBK.summary())

                        Constant Mean - GARCH Model Results                         
====================================================================================
Dep. Variable:                      Ret_DBK   R-squared:                       0.000
Mean Model:                   Constant Mean   Adj. R-squared:                  0.000
Vol Model:                            GARCH   Log-Likelihood:               -10842.2
Distribution:      Standardized Student's t   AIC:                           21694.3
Method:                  Maximum Likelihood   BIC:                           21726.9
                                              No. Observations:                 5008
Date:                      Thu, Jun 02 2022   Df Residuals:                     5007
Time:                              23:44:14   Df Model:                            1
                                  Mean Model                                  
==============================================================================
                  coef    std err          t      P>|t|       95.0% Conf. Int.
------------------------------------------------------------------------------
mu         -3.4032e-03  2.504e-02     -0.136      0.892 [-5.247e-02,4.567e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0389  1.206e-02      3.222  1.275e-03 [1.522e-02,6.250e-02]
alpha[1]       0.0676  8.938e-03      7.563  3.953e-14 [5.008e-02,8.511e-02]
beta[1]        0.9276  9.268e-03    100.084      0.000     [  0.909,  0.946]
                              Distribution                              
========================================================================
                 coef    std err          t      P>|t|  95.0% Conf. Int.
------------------------------------------------------------------------
nu             7.0362      0.667     10.543  5.460e-26 [  5.728,  8.344]
========================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(DBK_RET[-b:] / 100,
                        np.sqrt(Forecast_GARCHt_DBK\
                                .variance.iloc[-len(DBK_10):]
                                / 100)))
print('The RMSE value of GARCH-t model (DBK): {:.4f}'.format(rmse_arch))

The RMSE value of GARCH-t model (DBK): 0.2074

Bank of America Corp

# Specify GARCH model assumptions
GARCHt_BAC = arch_model(BAC_RET, p = 1,o=0, q = 1, vol = 'GARCH', dist = "StudentsT")

# Fit the model
GARCHt_result_BAC = GARCHt_BAC.fit(update_freq=5, disp="off")

# Get model estimated volatility
GARCHt_vol_BAC = GARCHt_result_BAC.conditional_volatility

# Forecasting
Prediction_GARCHt_BAC = GARCHt_result_BAC.forecast(horizon = 1, start = '2020-12-14')
Forecast_GARCHt_BAC = Prediction_GARCHt_BAC
Forecast_GARCHt_BAC

print(GARCHt_result_BAC.summary())

                        Constant Mean - GARCH Model Results                         
====================================================================================
Dep. Variable:                      Ret_BAC   R-squared:                       0.000
Mean Model:                   Constant Mean   Adj. R-squared:                  0.000
Vol Model:                            GARCH   Log-Likelihood:               -9923.29
Distribution:      Standardized Student's t   AIC:                           19856.6
Method:                  Maximum Likelihood   BIC:                           19889.2
                                              No. Observations:                 5008
Date:                      Thu, Jun 02 2022   Df Residuals:                     5007
Time:                              23:44:14   Df Model:                            1
                                 Mean Model                                 
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
mu             0.0418  1.793e-02      2.334  1.961e-02 [6.701e-03,7.698e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0280  9.141e-03      3.061  2.205e-03 [1.007e-02,4.590e-02]
alpha[1]       0.1001  1.548e-02      6.467  9.995e-11   [6.979e-02,  0.130]
beta[1]        0.8999  1.503e-02     59.879      0.000     [  0.870,  0.929]
                              Distribution                              
========================================================================
                 coef    std err          t      P>|t|  95.0% Conf. Int.
------------------------------------------------------------------------
nu             5.3811      0.409     13.142  1.885e-39 [  4.579,  6.184]
========================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(BAC_RET[-d:] / 100,
                        np.sqrt(Forecast_GARCHt_BAC\
                                .variance.iloc[-len(BAC_10):]
                                / 100)))
print('The RMSE value of GARCH-t model (BAC): {:.4f}'.format(rmse_arch))

The RMSE value of GARCH-t model (BAC): 0.2018

# Ploting Returns/Conditional Variance

## DBK
figure(figsize=(20, 6), dpi=100)
plt.plot(GARCHt_vol_DBK, color = 'red', label = 'Conditional Variance')
plt.plot(DBK_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GARCH-t: Returns/Conditional Variance (DBK)', fontsize=16)
plt.show()

## BAC
figure(figsize=(20, 6), dpi=100)
plt.plot(GARCHt_vol_BAC, color = 'red', label = 'Conditional Variance')
plt.plot(BAC_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GARCH-t: Returns/Conditional Variance (BAC)', fontsize=16)
plt.show()

# Ploting Actual Returns/Predicted Returns 

## DBK
plt.figure(figsize=(20, 6))
plt.plot(DBK_RET.iloc[-len(DBK_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GARCHt_DBK.variance.iloc[-len(DBK_10):] / 100,
        label='Predicted Returns')
plt.title('GARCH-t: Actual Returns/Predicted Returns (DBK)', fontsize=16)
plt.legend()
plt.show()

## BAC
plt.figure(figsize=(20, 6))
plt.plot(BAC_RET.iloc[-len(BAC_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GARCHt_BAC.variance.iloc[-len(BAC_10):] / 100,
        label='Predicted Returns')
plt.title('GARCH-t: Actual Returns/Predicted Returns (BAC)', fontsize=16)
plt.legend()
plt.show()

BMW

# Specify GARCH model assumptions
GARCHt_BMW = arch_model(BMW_RET, p = 1,o=0, q = 1, vol = 'GARCH', dist = "StudentsT")

# Fit the model
GARCHt_result_BMW = GARCHt_BMW.fit(update_freq=5, disp="off")

# Get model estimated volatility
GARCHt_vol_BMW = GARCHt_result_BMW.conditional_volatility

# Forecasting
Prediction_GARCHt_BMW = GARCHt_result_BMW.forecast(horizon = 1, start = '2020-12-14')
Forecast_GARCHt_BMW = Prediction_GARCHt_BMW
Forecast_GARCHt_BMW

print(GARCHt_result_BMW.summary())

                        Constant Mean - GARCH Model Results                         
====================================================================================
Dep. Variable:                      Ret_BMW   R-squared:                       0.000
Mean Model:                   Constant Mean   Adj. R-squared:                  0.000
Vol Model:                            GARCH   Log-Likelihood:               -9979.97
Distribution:      Standardized Student's t   AIC:                           19969.9
Method:                  Maximum Likelihood   BIC:                           20002.5
                                              No. Observations:                 5008
Date:                      Thu, Jun 02 2022   Df Residuals:                     5007
Time:                              23:44:15   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu             0.0238  2.100e-02      1.135      0.256 [-1.732e-02,6.498e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0219  7.483e-03      2.927  3.424e-03 [7.235e-03,3.657e-02]
alpha[1]       0.0555  8.646e-03      6.423  1.336e-10 [3.859e-02,7.248e-02]
beta[1]        0.9408  8.933e-03    105.322      0.000     [  0.923,  0.958]
                              Distribution                              
========================================================================
                 coef    std err          t      P>|t|  95.0% Conf. Int.
------------------------------------------------------------------------
nu             5.9814      0.480     12.465  1.156e-35 [  5.041,  6.922]
========================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(BMW_RET[-f:] / 100,
                        np.sqrt(Forecast_GARCHt_BMW\
                                .variance.iloc[-len(BMW_10):]
                                / 100)))
print('The RMSE value of GARCH-t model (BMW): {:.4f}'.format(rmse_arch))

The RMSE value of GARCH-t model (BMW): 0.1860

Ford

# Specify GARCH model assumptions
GARCHt_F = arch_model(F_RET, p = 1,o=0, q = 1, vol = 'GARCH', dist = "StudentsT")

# Fit the model
GARCHt_result_F = GARCHt_F.fit(update_freq=5, disp="off")

# Get model estimated volatility
GARCHt_vol_F = GARCHt_result_F.conditional_volatility

# Forecasting
Prediction_GARCHt_F = GARCHt_result_F.forecast(horizon = 1, start = '2020-12-14')
Forecast_GARCHt_F = Prediction_GARCHt_F
Forecast_GARCHt_F

print(GARCHt_result_F.summary())

                        Constant Mean - GARCH Model Results                         
====================================================================================
Dep. Variable:                        Ret_F   R-squared:                       0.000
Mean Model:                   Constant Mean   Adj. R-squared:                  0.000
Vol Model:                            GARCH   Log-Likelihood:               -10707.5
Distribution:      Standardized Student's t   AIC:                           21424.9
Method:                  Maximum Likelihood   BIC:                           21457.5
                                              No. Observations:                 5008
Date:                      Thu, Jun 02 2022   Df Residuals:                     5007
Time:                              23:44:16   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu            -0.0221  2.353e-02     -0.939      0.348 [-6.821e-02,2.403e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0334  1.599e-02      2.087  3.688e-02 [2.032e-03,6.470e-02]
alpha[1]       0.0619  1.500e-02      4.129  3.644e-05 [3.254e-02,9.135e-02]
beta[1]        0.9350  1.594e-02     58.645      0.000     [  0.904,  0.966]
                              Distribution                              
========================================================================
                 coef    std err          t      P>|t|  95.0% Conf. Int.
------------------------------------------------------------------------
nu             5.0964      0.368     13.855  1.185e-43 [  4.375,  5.817]
========================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(F_RET[-h:] / 100,
                        np.sqrt(Forecast_GARCHt_F\
                                .variance.iloc[-len(F_10):]
                                / 100)))
print('The RMSE value of GARCH-t model (Ford): {:.4f}'.format(rmse_arch))

The RMSE value of GARCH-t model (Ford): 0.2236

# Ploting Returns/Conditional Variance

## BMW
figure(figsize=(20, 6), dpi=100)
plt.plot(GARCHt_vol_BMW, color = 'red', label = 'Conditional Variance')
plt.plot(BMW_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GARCH-t: Returns/Conditional Variance (BMW)', fontsize=16)
plt.show()

## FORD
figure(figsize=(20, 6), dpi=100)
plt.plot(GARCHt_vol_F, color = 'red', label = 'Conditional Variance')
plt.plot(F_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GARCH-t: Returns/Conditional Variance (FORD)', fontsize=16)
plt.show()

# Ploting Actual Returns/Predicted Returns 

## BMW
plt.figure(figsize=(20, 6))
plt.plot(BMW_RET.iloc[-len(BMW_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GARCHt_BMW.variance.iloc[-len(BMW_10):] / 100,
        label='Predicted Returns')
plt.title('GARCH-t: Actual Returns/Predicted Returns (BMW)', fontsize=16)
plt.legend()
plt.show()

## FORD
plt.figure(figsize=(20, 6))
plt.plot(F_RET.iloc[-len(F_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GARCHt_F.variance.iloc[-len(F_10):] / 100,
        label='Predicted Returns')
plt.title('GARCH-t: Actual Returns/Predicted Returns (FORD)', fontsize=16)
plt.legend()
plt.show()

EGARCH model

Deutsche Bank AG

# Specify GARCH model assumptions
EGARCH_DBK = arch_model(DBK_RET, p = 1, q = 1, vol = 'EGARCH', dist = 'normal')

# Fit the model
EGARCH_result_DBK = EGARCH_DBK.fit(update_freq=5, disp="off")

# Get model estimated volatility
EGARCH_vol_DBK = EGARCH_result_DBK.conditional_volatility

# Forecasting
Prediction_EGARCH_DBK = EGARCH_result_DBK.forecast(horizon = 1, start = '2020-12-14')
Forecast_EGARCH_DBK = Prediction_EGARCH_DBK
Forecast_EGARCH_DBK

print(EGARCH_result_DBK.summary())

                     Constant Mean - EGARCH Model Results                     
==============================================================================
Dep. Variable:                Ret_DBK   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                     EGARCH   Log-Likelihood:               -10941.9
Distribution:                  Normal   AIC:                           21891.7
Method:            Maximum Likelihood   BIC:                           21917.8
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:17   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu         4.5026e-04  2.620e-02  1.718e-02      0.986 [-5.091e-02,5.181e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0198  4.982e-03      3.973  7.099e-05 [1.003e-02,2.956e-02]
alpha[1]       0.1554  1.832e-02      8.482  2.212e-17     [  0.120,  0.191]
beta[1]        0.9911  2.730e-03    363.083      0.000     [  0.986,  0.996]
============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(DBK_RET[-b:] / 100,
                        np.sqrt(Forecast_EGARCH_DBK\
                                .variance.iloc[-len(DBK_10):]
                                / 100)))
print('The RMSE value of EGARCH model (DBK): {:.4f}'.format(rmse_arch))

The RMSE value of EGARCH model (DBK): 0.2161

Bank of America Corp

# Specify GARCH model assumptions
EGARCH_BAC = arch_model(BAC_RET, p = 1, q = 1, vol = 'EGARCH', dist = 'normal')

# Fit the model
EGARCH_result_BAC = EGARCH_BAC.fit(update_freq=5, disp="off")

# Get model estimated volatility
EGARCH_vol_BAC = EGARCH_result_BAC.conditional_volatility

# Forecasting
Prediction_EGARCH_BAC = EGARCH_result_BAC.forecast(horizon = 1, start = '2020-12-14')
Forecast_EGARCH_BAC = Prediction_EGARCH_BAC
Forecast_EGARCH_BAC

print(EGARCH_result_BAC.summary())

                     Constant Mean - EGARCH Model Results                     
==============================================================================
Dep. Variable:                Ret_BAC   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                     EGARCH   Log-Likelihood:               -10161.4
Distribution:                  Normal   AIC:                           20330.7
Method:            Maximum Likelihood   BIC:                           20356.8
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:17   Df Model:                            1
                                 Mean Model                                 
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
mu             0.0442  1.355e-03     32.660 5.707e-234 [4.159e-02,4.689e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0232  5.739e-03      4.039  5.377e-05 [1.193e-02,3.443e-02]
alpha[1]       0.1705  3.400e-02      5.013  5.360e-07     [  0.104,  0.237]
beta[1]        0.9894  3.086e-03    320.639      0.000     [  0.983,  0.995]
============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(BAC_RET[-d:] / 100,
                        np.sqrt(Forecast_EGARCH_BAC\
                                .variance.iloc[-len(BAC_10):]
                                / 100)))
print('The RMSE value of EGARCH model (BAC): {:.4f}'.format(rmse_arch))

The RMSE value of EGARCH model (BAC): 0.1997

# Ploting Returns/Conditional Variance

## DBK
figure(figsize=(20, 6), dpi=100)
plt.plot(EGARCH_vol_DBK, color = 'red', label = 'Conditional Variance')
plt.plot(DBK_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('EGARCH: Returns/Conditional Variance (DBK)', fontsize=16)
plt.show()

## BAC
figure(figsize=(20, 6), dpi=100)
plt.plot(EGARCH_vol_BAC, color = 'red', label = 'Conditional Variance')
plt.plot(BAC_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('EGARCH: Returns/Conditional Variance (BAC)', fontsize=16)
plt.show()

# Ploting Actual Returns/Predicted Returns 

## DBK
plt.figure(figsize=(20, 6))
plt.plot(DBK_RET.iloc[-len(DBK_90):] / 100, label='Actual Returns')
plt.plot(Forecast_EGARCH_DBK.variance.iloc[-len(DBK_10):] / 100,
        label='Predicted Returns')
plt.title('EGARCH: Actual Returns/Predicted Returns (DBK)', fontsize=16)
plt.legend()
plt.show()

## BAC
plt.figure(figsize=(20, 6))
plt.plot(BAC_RET.iloc[-len(BAC_90):] / 100, label='Actual Returns')
plt.plot(Forecast_EGARCH_BAC.variance.iloc[-len(BAC_10):] / 100,
        label='Predicted Returns')
plt.title('EGARCH: Actual Returns/Predicted Returns (BAC)', fontsize=16)
plt.legend()
plt.show()

BMW

# Specify GARCH model assumptions
EGARCH_BMW = arch_model(BMW_RET, p = 1, q = 1, vol = 'EGARCH', dist = 'normal')

# Fit the model
EGARCH_result_BMW = EGARCH_BMW.fit(update_freq=5, disp="off")

# Get model estimated volatility
EGARCH_vol_BMW = EGARCH_result_BMW.conditional_volatility

# Forecasting
Prediction_EGARCH_BMW = EGARCH_result_BMW.forecast(horizon = 1, start = '2020-12-14')
Forecast_EGARCH_BMW = Prediction_EGARCH_BMW
Forecast_EGARCH_BMW

print(EGARCH_result_BMW.summary())

                     Constant Mean - EGARCH Model Results                     
==============================================================================
Dep. Variable:                Ret_BMW   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                     EGARCH   Log-Likelihood:               -10114.9
Distribution:                  Normal   AIC:                           20237.7
Method:            Maximum Likelihood   BIC:                           20263.8
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:19   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu             0.0333  2.317e-02      1.437      0.151 [-1.212e-02,7.868e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0200  5.101e-03      3.927  8.605e-05 [1.003e-02,3.003e-02]
alpha[1]       0.1461  1.954e-02      7.479  7.471e-14     [  0.108,  0.184]
beta[1]        0.9890  3.205e-03    308.635      0.000     [  0.983,  0.995]
============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(BMW_RET[-f:] / 100,
                        np.sqrt(Forecast_EGARCH_BMW\
                                .variance.iloc[-len(BMW_10):]
                                / 100)))
print('The RMSE value of EGARCH model (BMW): {:.4f}'.format(rmse_arch))

The RMSE value of EGARCH model (BMW): 0.1836

Ford

# Specify GARCH model assumptions
EGARCH_F = arch_model(F_RET, p = 1, q = 1, vol = 'EGARCH', dist = 'normal')

# Fit the model
EGARCH_result_F = EGARCH_F.fit(update_freq=5, disp="off")

# Get model estimated volatility
EGARCH_vol_F = EGARCH_result_F.conditional_volatility

# Forecasting
Prediction_EGARCH_F = EGARCH_result_F.forecast(horizon = 1, start = '2020-12-14')
Forecast_EGARCH_F = Prediction_EGARCH_F
Forecast_EGARCH_F

print(EGARCH_result_F.summary())

                     Constant Mean - EGARCH Model Results                     
==============================================================================
Dep. Variable:                  Ret_F   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                     EGARCH   Log-Likelihood:               -10931.5
Distribution:                  Normal   AIC:                           21871.0
Method:            Maximum Likelihood   BIC:                           21897.1
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:19   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu            -0.0398  2.834e-02     -1.405      0.160 [-9.536e-02,1.574e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0328  1.434e-02      2.285  2.228e-02 [4.669e-03,6.089e-02]
alpha[1]       0.1614  3.715e-02      4.346  1.386e-05   [8.864e-02,  0.234]
beta[1]        0.9850  7.668e-03    128.447      0.000     [  0.970,  1.000]
============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(F_RET[-h:] / 100,
                        np.sqrt(Forecast_EGARCH_F\
                                .variance.iloc[-len(F_10):]
                                / 100)))
print('The RMSE value of EGARCH model (FORD): {:.4f}'.format(rmse_arch))

The RMSE value of EGARCH model (FORD): 0.2243

# Ploting Returns/Conditional Variance

## BMW
figure(figsize=(20, 6), dpi=100)
plt.plot(EGARCH_vol_BMW, color = 'red', label = 'Conditional Variance')
plt.plot(BMW_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('EGARCH: Returns/Conditional Variance (BMW)', fontsize=16)
plt.show()

## FORD
figure(figsize=(20, 6), dpi=100)
plt.plot(EGARCH_vol_F, color = 'red', label = 'Conditional Variance')
plt.plot(F_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('EGARCH: Returns/Conditional Variance (FORD)', fontsize=16)
plt.show()

# Ploting Actual Returns/Predicted Returns 

## BMW
plt.figure(figsize=(20, 6))
plt.plot(BMW_RET.iloc[-len(BMW_90):] / 100, label='Actual Returns')
plt.plot(Forecast_EGARCH_BMW.variance.iloc[-len(BMW_10):] / 100,
        label='Predicted Returns')
plt.title('EGARCH: Actual Returns/Predicted Returns (BMW)', fontsize=16)
plt.legend()
plt.show()

## FORD
plt.figure(figsize=(20, 6))
plt.plot(F_RET.iloc[-len(F_90):] / 100, label='Actual Returns')
plt.plot(Forecast_EGARCH_F.variance.iloc[-len(F_10):] / 100,
        label='Predicted Returns')
plt.title('EGARCH: Actual Returns/Predicted Returns (FORD)', fontsize=16)
plt.legend()
plt.show()

GJR-GARCH model

Deutsche Bank AG

# Specify GARCH model assumptions
GJR_GARCH_DBK = arch_model(DBK_RET, p=1, o=1, q=1, dist = 'normal')

# Fit the model
GJR_GARCH_result_DBK = GJR_GARCH_DBK.fit(update_freq=5, disp="off")

# Get model estimated volatility
GJR_GARCH_vol_DBK = GJR_GARCH_result_DBK.conditional_volatility

# Forecasting
Prediction_GJR_GARCH_DBK = GJR_GARCH_result_DBK.forecast(horizon = 1, start = '2020-12-14')
Forecast_GJR_GARCH_DBK = Prediction_GJR_GARCH_DBK
Forecast_GJR_GARCH_DBK

print(GJR_GARCH_result_DBK.summary())

                   Constant Mean - GJR-GARCH Model Results                    
==============================================================================
Dep. Variable:                Ret_DBK   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                  GJR-GARCH   Log-Likelihood:               -10921.4
Distribution:                  Normal   AIC:                           21852.8
Method:            Maximum Likelihood   BIC:                           21885.4
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:20   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu            -0.0359  2.608e-02     -1.375      0.169 [-8.697e-02,1.527e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0332  1.248e-02      2.662  7.763e-03 [8.763e-03,5.768e-02]
alpha[1]       0.0307  1.123e-02      2.736  6.215e-03 [8.718e-03,5.274e-02]
gamma[1]       0.0536  1.197e-02      4.479  7.486e-06 [3.016e-02,7.709e-02]
beta[1]        0.9379  1.185e-02     79.181      0.000     [  0.915,  0.961]
============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(DBK_RET[-b:] / 100,
                        np.sqrt(Forecast_GJR_GARCH_DBK\
                                .variance.iloc[-len(DBK_10):]
                                / 100)))
print('The RMSE value of GJR-GARCH model (DBK): {:.4f}'.format(rmse_arch))

The RMSE value of GJR-GARCH model (DBK): 0.2072

Bank of America Corp

# Specify GARCH model assumptions
GJR_GARCH_BAC = arch_model(BAC_RET, p=1, o=1, q=1, dist = 'normal')

# Fit the model
GJR_GARCH_result_BAC = GJR_GARCH_BAC.fit(update_freq=5, disp="off")

# Get model estimated volatility
GJR_GARCH_vol_BAC = GJR_GARCH_result_BAC.conditional_volatility

# Forecasting
Prediction_GJR_GARCH_BAC = GJR_GARCH_result_BAC.forecast(horizon = 1, start = '2020-12-14')
Forecast_GJR_GARCH_BAC = Prediction_GJR_GARCH_BAC
Forecast_GJR_GARCH_BAC

print(GJR_GARCH_result_BAC.summary())

                   Constant Mean - GJR-GARCH Model Results                    
==============================================================================
Dep. Variable:                Ret_BAC   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                  GJR-GARCH   Log-Likelihood:               -10116.7
Distribution:                  Normal   AIC:                           20243.3
Method:            Maximum Likelihood   BIC:                           20275.9
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:20   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu         4.6621e-03  2.240e-02      0.208      0.835 [-3.923e-02,4.856e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0434  2.124e-02      2.041  4.124e-02 [1.724e-03,8.499e-02]
alpha[1]       0.0395  1.712e-02      2.306  2.113e-02 [5.916e-03,7.301e-02]
gamma[1]       0.0839  2.290e-02      3.664  2.478e-04   [3.903e-02,  0.129]
beta[1]        0.9108  2.629e-02     34.652 4.172e-263     [  0.859,  0.962]
============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(BAC_RET[-d:] / 100,
                        np.sqrt(Forecast_GJR_GARCH_BAC\
                                .variance.iloc[-len(BAC_10):]
                                / 100)))
print('The RMSE value of GJR-GARCH model (BAC): {:.4f}'.format(rmse_arch))

The RMSE value of GJR-GARCH model (BAC): 0.1787

# Ploting Returns/Conditional Variance

## DBK
figure(figsize=(20, 6), dpi=100)
plt.plot(GJR_GARCH_vol_DBK, color = 'red', label = 'Conditional Variance')
plt.plot(DBK_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GJR-GARCH: Returns/Conditional Variance (DBK)', fontsize=16)
plt.show()

## BAC
figure(figsize=(20, 6), dpi=100)
plt.plot(GJR_GARCH_vol_BAC, color = 'red', label = 'Conditional Variance')
plt.plot(BAC_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GJR-GARCH: Returns/Conditional Variance (BAC)', fontsize=16)
plt.show()

# Ploting Actual Returns/Predicted Returns 

## DBK
plt.figure(figsize=(20, 6))
plt.plot(DBK_RET.iloc[-len(DBK_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GJR_GARCH_DBK.variance.iloc[-len(DBK_10):] / 100,
        label='Predicted Returns')
plt.title('GJR-GARCH: Actual Returns/Predicted Returns (DBK)', fontsize=16)
plt.legend()
plt.show()

## BAC
plt.figure(figsize=(20, 6))
plt.plot(BAC_RET.iloc[-len(BAC_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GJR_GARCH_BAC.variance.iloc[-len(BAC_10):] / 100,
        label='Predicted Returns')
plt.title('GJR-GARCH: Actual Returns/Predicted Returns (BAC)', fontsize=16)
plt.legend()
plt.show()

BMW

# Specify GARCH model assumptions
GJR_GARCH_BMW = arch_model(BMW_RET, p=1, o=1, q=1, dist = 'normal')

# Fit the model
GJR_GARCH_result_BMW = GJR_GARCH_BMW.fit(update_freq=5, disp="off")

# Get model estimated volatility
GJR_GARCH_vol_BMW = GJR_GARCH_result_BMW.conditional_volatility

# Forecasting
Prediction_GJR_GARCH_BMW = GJR_GARCH_result_BMW.forecast(horizon = 1, start = '2020-12-14')
Forecast_GJR_GARCH_BMW = Prediction_GJR_GARCH_BMW
Forecast_GJR_GARCH_BMW

print(GJR_GARCH_result_BMW.summary())

                   Constant Mean - GJR-GARCH Model Results                    
==============================================================================
Dep. Variable:                Ret_BMW   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                  GJR-GARCH   Log-Likelihood:               -10085.6
Distribution:                  Normal   AIC:                           20181.2
Method:            Maximum Likelihood   BIC:                           20213.8
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:22   Df Model:                            1
                                  Mean Model                                 
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
mu         3.6091e-03  2.275e-02      0.159      0.874 [-4.098e-02,4.820e-02]
                              Volatility Model                              
============================================================================
                 coef    std err          t      P>|t|      95.0% Conf. Int.
----------------------------------------------------------------------------
omega          0.0340  1.134e-02      3.000  2.698e-03 [1.180e-02,5.627e-02]
alpha[1]       0.0236  7.849e-03      3.013  2.587e-03 [8.264e-03,3.903e-02]
gamma[1]       0.0637  1.476e-02      4.317  1.583e-05 [3.478e-02,9.263e-02]
beta[1]        0.9368  1.148e-02     81.625      0.000     [  0.914,  0.959]
============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(BMW_RET[-f:] / 100,
                        np.sqrt(Forecast_GJR_GARCH_BMW\
                                .variance.iloc[-len(BMW_10):]
                                / 100)))
print('The RMSE value of GJR-GARCH model (BMW): {:.4f}'.format(rmse_arch))

The RMSE value of GJR-GARCH model (BMW): 0.1722

Ford

# Specify GARCH model assumptions
GJR_GARCH_F = arch_model(F_RET, p=1, o=1, q=1, dist = 'normal')

# Fit the model
GJR_GARCH_result_F = GJR_GARCH_F.fit(update_freq=5, disp="off")

# Get model estimated volatility
GJR_GARCH_vol_F = GJR_GARCH_result_F.conditional_volatility

# Forecasting
Prediction_GJR_GARCH_F = GJR_GARCH_result_F.forecast(horizon = 1, start = '2020-12-14')
Forecast_GJR_GARCH_F = Prediction_GJR_GARCH_F
Forecast_GJR_GARCH_F

print(GJR_GARCH_result_F.summary())

                   Constant Mean - GJR-GARCH Model Results                    
==============================================================================
Dep. Variable:                  Ret_F   R-squared:                       0.000
Mean Model:             Constant Mean   Adj. R-squared:                  0.000
Vol Model:                  GJR-GARCH   Log-Likelihood:               -10943.6
Distribution:                  Normal   AIC:                           21897.3
Method:            Maximum Likelihood   BIC:                           21929.8
                                        No. Observations:                 5008
Date:                Thu, Jun 02 2022   Df Residuals:                     5007
Time:                        23:44:22   Df Model:                            1
                                 Mean Model                                
===========================================================================
                 coef    std err          t      P>|t|     95.0% Conf. Int.
---------------------------------------------------------------------------
mu            -0.0540  2.744e-02     -1.967  4.920e-02 [ -0.108,-1.888e-04]
                               Volatility Model                              
=============================================================================
                 coef    std err          t      P>|t|       95.0% Conf. Int.
-----------------------------------------------------------------------------
omega          0.0630  3.864e-02      1.630      0.103   [-1.275e-02,  0.139]
alpha[1]       0.0516  2.526e-02      2.043  4.106e-02    [2.094e-03,  0.101]
gamma[1]       0.0184  1.284e-02      1.430      0.153 [-6.807e-03,4.351e-02]
beta[1]        0.9288  2.771e-02     33.516 2.856e-246      [  0.875,  0.983]
=============================================================================

Covariance estimator: robust

# Calculate the RMSE
rmse_arch = np.sqrt(mse(F_RET[-h:] / 100,
                        np.sqrt(Forecast_GJR_GARCH_F\
                                .variance.iloc[-len(F_10):]
                                / 100)))
print('The RMSE value of GJR-GARCH model (FORD): {:.4f}'.format(rmse_arch))

The RMSE value of GJR-GARCH model (FORD): 0.2156

# Ploting Returns/Conditional Variance

## BMW
figure(figsize=(20, 6), dpi=100)
plt.plot(GJR_GARCH_vol_BMW, color = 'red', label = 'Conditional Variance')
plt.plot(BMW_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GJR-GARCH: Returns/Conditional Variance (BMW)', fontsize=16)
plt.show()

## FORD
figure(figsize=(20, 6), dpi=100)
plt.plot(GJR_GARCH_vol_F, color = 'red', label = 'Conditional Variance')
plt.plot(F_RET, color = 'blue', 
         label = 'Daily Returns', alpha = 0.4)
plt.legend(loc = 'upper right')
plt.title('GJR-GARCH: Returns/Conditional Variance (FORD)', fontsize=16)
plt.show()

# Ploting Actual Returns/Predicted Returns 

## BMW
plt.figure(figsize=(20, 6))
plt.plot(BMW_RET.iloc[-len(BMW_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GJR_GARCH_BMW.variance.iloc[-len(BMW_10):] / 100,
        label='Predicted Returns')
plt.title('GJR-GARCH: Actual Returns/Predicted Returns (BMW)', fontsize=16)
plt.legend()
plt.show()

## FORD
plt.figure(figsize=(20, 6))
plt.plot(F_RET.iloc[-len(F_90):] / 100, label='Actual Returns')
plt.plot(Forecast_GJR_GARCH_F.variance.iloc[-len(F_10):] / 100,
        label='Predicted Returns')
plt.title('GJR-GARCH: Actual Returns/Predicted Returns (FORD)', fontsize=16)
plt.legend()
plt.show()

Data Science models

LSTM

Deutsche Bank AG

# transform a time series dataset into a supervised learning dataset (Input : Output)

## Adjust time format 
def str_to_datetime(s):
    split = s.split('-')
    year, month, day = int(split[0]), int(split[1]), int(split[2])
    return datetime.datetime(year=year, month=month, day=day)

datetime_object = str_to_datetime('2001-01-04')

## Create a function 
def DBK_to_windowed_DBK(DBK_RET, first_date_str, last_date_str, n=3):
    first_date = str_to_datetime(first_date_str)
    last_date  = str_to_datetime(last_date_str)
    
    target_date = first_date
    
    dates_DBK = []
    X, Y = [], []
    
    last_time = False
    while True:
        DBK_subset = DBK_RET.loc[:target_date].tail(n+1)
        
        if len(DBK_subset) != n+1:
            print(f'Error: Window of size {n} is too large for date {target_date}')
            return
        
        values = DBK_subset['Ret_DBK'].to_numpy()
        x, y = values[:-1], values[-1]
        
        dates_DBK.append(target_date)
        X.append(x)
        Y.append(y)
        
        next_week = DBK_RET.loc[target_date:target_date+datetime.timedelta(days=7)]
        next_datetime_str = str(next_week.head(2).tail(1).index.values[0])
        next_date_str = next_datetime_str.split('T')[0]
        year_month_day = next_date_str.split('-')
        year, month, day = year_month_day
        next_date = datetime.datetime(day=int(day), month=int(month), year=int(year))
        
        if last_time:
            break
        
        target_date = next_date
        
        if target_date == last_date:
            last_time = True
    ret_DBK = pd.DataFrame({})
    ret_DBK['Target Date'] = dates_DBK
    
    X = np.array(X)
    for i in range(0, n):
        X[:, i]
        ret_DBK[f'Target-{n-i}'] = X[:, i]
        
    ret_DBK['Target'] = Y
    
    return ret_DBK

## Start day second time around: '2020-01-03'
windowed_DBK = DBK_to_windowed_DBK(DBK_RET, 
                                '2020-01-03', 
                                '2020-12-30', 
                                n=3)
windowed_DBK.head(n=10)

	Target Date	Target-3	Target-2	Target-1	Target
0	2020-01-03	-0.761316	-2.275915	0.159150	-1.329061
1	2020-01-06	-2.275915	0.159150	-1.329061	-0.900596
2	2020-01-07	0.159150	-1.329061	-0.900596	3.406856
3	2020-01-08	-1.329061	-0.900596	3.406856	3.320630
4	2020-01-09	-0.900596	3.406856	3.320630	0.402574
5	2020-01-10	3.406856	3.320630	0.402574	-0.272532
6	2020-01-13	3.320630	0.402574	-0.272532	-1.505760
7	2020-01-14	0.402574	-0.272532	-1.505760	2.256665
8	2020-01-15	-0.272532	-1.505760	2.256665	-2.388675
9	2020-01-16	-1.505760	2.256665	-2.388675	0.776371

#Convert our new dataset into numpy arrays (to feed it directly into a tensorflow model)
def windowed_DBK_to_date_X_y(windowed_dataframe):
    DBK_as_np = windowed_dataframe.to_numpy()
    
    dates_DBK = DBK_as_np[:, 0] 
    
    middle_matrix = DBK_as_np[:, 1:-1]
    X_DBK = middle_matrix.reshape((len(dates_DBK), middle_matrix.shape[1], 1))
    
    Y_DBK = DBK_as_np[:, -1]
    
    return dates_DBK, X_DBK.astype(np.float32), Y_DBK.astype(np.float32)

dates_DBK, X_DBK, y_DBK = windowed_DBK_to_date_X_y(windowed_DBK)

dates_DBK.shape, X_DBK.shape, y_DBK.shape

((237,), (237, 3, 1), (237,))

# Split the data into training, validation and testing partitions 
q_85_DBK = int(len(dates_DBK) * .85)
q_95_DBK = int(len(dates_DBK) * .95)

dates_train_DBK, X_train_DBK, y_train_DBK = dates_DBK[:q_85_DBK], X_DBK[:q_85_DBK], y_DBK[:q_85_DBK]
dates_val_DBK, X_val_DBK, y_val_DBK = dates_DBK[q_85_DBK:q_95_DBK], X_DBK[q_85_DBK:q_95_DBK], y_DBK[q_85_DBK:q_95_DBK]
dates_test_DBK, X_test_DBK, y_test_DBK = dates_DBK[q_95_DBK:], X_DBK[q_95_DBK:], y_DBK[q_95_DBK:]

# Create & train the LSTM model 
model_DBK = Sequential([layers.Input((3, 1)),
                    layers.LSTM(264),
                    layers.Dense(132, activation='relu'),
                    layers.Dense(132, activation='relu'),
                    layers.Dense(1)])

model_DBK.compile(loss='mse', 
              optimizer=Adam(learning_rate=0.001),
              metrics=['mean_absolute_error'])

# Fitting the LSTM model 
model_DBK.fit(X_train_DBK, y_train_DBK, validation_data=(X_val_DBK, y_val_DBK), epochs=1000)

# Forecasting
train_predictions_DBK = model_DBK.predict(X_train_DBK).flatten()
val_predictions_DBK = model_DBK.predict(X_val_DBK).flatten()
test_predictions_DBK = model_DBK.predict(X_test_DBK).flatten()

2022-06-02 23:44:24.609793: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.

Epoch 1/1000
7/7 [==============================] - 4s 122ms/step - loss: 14.7010 - mean_absolute_error: 2.6141 - val_loss: 3.1132 - val_mean_absolute_error: 1.3688
Epoch 2/1000
7/7 [==============================] - 0s 26ms/step - loss: 14.5905 - mean_absolute_error: 2.6062 - val_loss: 3.0840 - val_mean_absolute_error: 1.3528
Epoch 3/1000
7/7 [==============================] - 0s 23ms/step - loss: 14.4811 - mean_absolute_error: 2.5987 - val_loss: 3.0932 - val_mean_absolute_error: 1.3597
Epoch 4/1000
7/7 [==============================] - 0s 25ms/step - loss: 14.3076 - mean_absolute_error: 2.5833 - val_loss: 3.0384 - val_mean_absolute_error: 1.3374
Epoch 5/1000
7/7 [==============================] - 0s 22ms/step - loss: 14.1136 - mean_absolute_error: 2.5686 - val_loss: 2.9454 - val_mean_absolute_error: 1.3032
Epoch 6/1000
7/7 [==============================] - 0s 21ms/step - loss: 13.9088 - mean_absolute_error: 2.5453 - val_loss: 2.8834 - val_mean_absolute_error: 1.2991
Epoch 7/1000
7/7 [==============================] - 0s 22ms/step - loss: 13.7648 - mean_absolute_error: 2.5306 - val_loss: 2.7628 - val_mean_absolute_error: 1.2890
Epoch 8/1000
7/7 [==============================] - 0s 23ms/step - loss: 13.5773 - mean_absolute_error: 2.5107 - val_loss: 2.6400 - val_mean_absolute_error: 1.2694
Epoch 9/1000
7/7 [==============================] - 0s 25ms/step - loss: 13.3618 - mean_absolute_error: 2.4755 - val_loss: 2.6227 - val_mean_absolute_error: 1.2631
Epoch 10/1000
7/7 [==============================] - 0s 27ms/step - loss: 13.1538 - mean_absolute_error: 2.4533 - val_loss: 2.6881 - val_mean_absolute_error: 1.2866
Epoch 11/1000
7/7 [==============================] - 0s 25ms/step - loss: 12.9437 - mean_absolute_error: 2.4376 - val_loss: 2.8791 - val_mean_absolute_error: 1.3257
Epoch 12/1000
7/7 [==============================] - 0s 27ms/step - loss: 12.7502 - mean_absolute_error: 2.4277 - val_loss: 2.7595 - val_mean_absolute_error: 1.3001
Epoch 13/1000
7/7 [==============================] - 0s 23ms/step - loss: 12.6433 - mean_absolute_error: 2.4077 - val_loss: 2.7993 - val_mean_absolute_error: 1.3203
Epoch 14/1000
7/7 [==============================] - 0s 29ms/step - loss: 12.4731 - mean_absolute_error: 2.3750 - val_loss: 2.7050 - val_mean_absolute_error: 1.2983
Epoch 15/1000
7/7 [==============================] - 0s 22ms/step - loss: 12.5268 - mean_absolute_error: 2.4167 - val_loss: 2.8794 - val_mean_absolute_error: 1.3378
Epoch 16/1000
7/7 [==============================] - 0s 22ms/step - loss: 12.2361 - mean_absolute_error: 2.3606 - val_loss: 2.7781 - val_mean_absolute_error: 1.3109
Epoch 17/1000
7/7 [==============================] - 0s 21ms/step - loss: 12.2948 - mean_absolute_error: 2.3431 - val_loss: 2.7946 - val_mean_absolute_error: 1.2975
Epoch 18/1000
7/7 [==============================] - 0s 24ms/step - loss: 11.6972 - mean_absolute_error: 2.3051 - val_loss: 2.8471 - val_mean_absolute_error: 1.3248
Epoch 19/1000
7/7 [==============================] - 0s 33ms/step - loss: 11.4407 - mean_absolute_error: 2.2980 - val_loss: 2.7638 - val_mean_absolute_error: 1.3069
Epoch 20/1000
7/7 [==============================] - 0s 26ms/step - loss: 11.1275 - mean_absolute_error: 2.2878 - val_loss: 2.8128 - val_mean_absolute_error: 1.3082
Epoch 21/1000
7/7 [==============================] - 0s 23ms/step - loss: 11.0212 - mean_absolute_error: 2.2731 - val_loss: 2.9761 - val_mean_absolute_error: 1.3750
Epoch 22/1000
7/7 [==============================] - 0s 24ms/step - loss: 10.8299 - mean_absolute_error: 2.2403 - val_loss: 2.8029 - val_mean_absolute_error: 1.3035
Epoch 23/1000
7/7 [==============================] - 0s 25ms/step - loss: 10.5139 - mean_absolute_error: 2.2383 - val_loss: 2.6976 - val_mean_absolute_error: 1.2761
Epoch 24/1000
7/7 [==============================] - 0s 26ms/step - loss: 10.1908 - mean_absolute_error: 2.2027 - val_loss: 2.8765 - val_mean_absolute_error: 1.3102
Epoch 25/1000
7/7 [==============================] - 0s 27ms/step - loss: 10.0326 - mean_absolute_error: 2.2165 - val_loss: 2.9509 - val_mean_absolute_error: 1.3407
Epoch 26/1000
7/7 [==============================] - 0s 24ms/step - loss: 9.8691 - mean_absolute_error: 2.2210 - val_loss: 2.8133 - val_mean_absolute_error: 1.2918
Epoch 27/1000
7/7 [==============================] - 0s 25ms/step - loss: 9.5506 - mean_absolute_error: 2.1833 - val_loss: 2.6727 - val_mean_absolute_error: 1.2467
Epoch 28/1000
7/7 [==============================] - 0s 21ms/step - loss: 9.3307 - mean_absolute_error: 2.1346 - val_loss: 2.6861 - val_mean_absolute_error: 1.2194
Epoch 29/1000
7/7 [==============================] - 0s 26ms/step - loss: 9.3968 - mean_absolute_error: 2.1445 - val_loss: 2.7305 - val_mean_absolute_error: 1.2429
Epoch 30/1000
7/7 [==============================] - 0s 27ms/step - loss: 9.1597 - mean_absolute_error: 2.1554 - val_loss: 2.6577 - val_mean_absolute_error: 1.2522
Epoch 31/1000
7/7 [==============================] - 0s 24ms/step - loss: 9.2594 - mean_absolute_error: 2.1797 - val_loss: 2.8002 - val_mean_absolute_error: 1.2681
Epoch 32/1000
7/7 [==============================] - 0s 28ms/step - loss: 9.3023 - mean_absolute_error: 2.1931 - val_loss: 2.7071 - val_mean_absolute_error: 1.2324
Epoch 33/1000
7/7 [==============================] - 0s 27ms/step - loss: 9.1654 - mean_absolute_error: 2.1399 - val_loss: 2.6461 - val_mean_absolute_error: 1.2169
Epoch 34/1000
7/7 [==============================] - 0s 26ms/step - loss: 9.5702 - mean_absolute_error: 2.1809 - val_loss: 2.6669 - val_mean_absolute_error: 1.2198
Epoch 35/1000
7/7 [==============================] - 0s 24ms/step - loss: 10.5184 - mean_absolute_error: 2.2704 - val_loss: 2.8517 - val_mean_absolute_error: 1.3055
Epoch 36/1000
7/7 [==============================] - 0s 23ms/step - loss: 9.0346 - mean_absolute_error: 2.1895 - val_loss: 2.9752 - val_mean_absolute_error: 1.3545
Epoch 37/1000
7/7 [==============================] - 0s 25ms/step - loss: 9.3243 - mean_absolute_error: 2.1902 - val_loss: 2.9717 - val_mean_absolute_error: 1.3441
Epoch 38/1000
7/7 [==============================] - 0s 22ms/step - loss: 8.8970 - mean_absolute_error: 2.1239 - val_loss: 2.8492 - val_mean_absolute_error: 1.2746
Epoch 39/1000
7/7 [==============================] - 0s 31ms/step - loss: 9.3469 - mean_absolute_error: 2.1962 - val_loss: 2.8221 - val_mean_absolute_error: 1.2798
Epoch 40/1000
7/7 [==============================] - 0s 22ms/step - loss: 8.4664 - mean_absolute_error: 2.0592 - val_loss: 2.8088 - val_mean_absolute_error: 1.2965
Epoch 41/1000
7/7 [==============================] - 0s 24ms/step - loss: 8.7978 - mean_absolute_error: 2.1207 - val_loss: 2.9737 - val_mean_absolute_error: 1.3438
Epoch 42/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.6293 - mean_absolute_error: 2.1197 - val_loss: 2.9427 - val_mean_absolute_error: 1.3143
Epoch 43/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.9756 - mean_absolute_error: 2.1472 - val_loss: 2.7333 - val_mean_absolute_error: 1.2326
Epoch 44/1000
7/7 [==============================] - 0s 36ms/step - loss: 9.0886 - mean_absolute_error: 2.1485 - val_loss: 3.1640 - val_mean_absolute_error: 1.4389
Epoch 45/1000
7/7 [==============================] - 0s 22ms/step - loss: 8.6756 - mean_absolute_error: 2.1585 - val_loss: 3.3187 - val_mean_absolute_error: 1.4421
Epoch 46/1000
7/7 [==============================] - 0s 22ms/step - loss: 8.8070 - mean_absolute_error: 2.1739 - val_loss: 2.7803 - val_mean_absolute_error: 1.2368
Epoch 47/1000
7/7 [==============================] - 0s 26ms/step - loss: 8.2111 - mean_absolute_error: 2.0360 - val_loss: 2.6428 - val_mean_absolute_error: 1.2269
Epoch 48/1000
7/7 [==============================] - 0s 22ms/step - loss: 8.4390 - mean_absolute_error: 2.0674 - val_loss: 2.6741 - val_mean_absolute_error: 1.2222
Epoch 49/1000
7/7 [==============================] - 0s 20ms/step - loss: 8.0463 - mean_absolute_error: 2.0291 - val_loss: 2.7935 - val_mean_absolute_error: 1.2538
Epoch 50/1000
7/7 [==============================] - 0s 21ms/step - loss: 8.4353 - mean_absolute_error: 2.0635 - val_loss: 2.8202 - val_mean_absolute_error: 1.3002
Epoch 51/1000
7/7 [==============================] - 0s 22ms/step - loss: 8.0048 - mean_absolute_error: 2.0159 - val_loss: 2.7672 - val_mean_absolute_error: 1.2758
Epoch 52/1000
7/7 [==============================] - 0s 21ms/step - loss: 8.2423 - mean_absolute_error: 2.0720 - val_loss: 2.7993 - val_mean_absolute_error: 1.2875
Epoch 53/1000
7/7 [==============================] - 0s 27ms/step - loss: 8.0038 - mean_absolute_error: 2.0101 - val_loss: 2.6769 - val_mean_absolute_error: 1.2558
Epoch 54/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.3180 - mean_absolute_error: 2.0636 - val_loss: 3.0298 - val_mean_absolute_error: 1.3974
Epoch 55/1000
7/7 [==============================] - 0s 18ms/step - loss: 8.0118 - mean_absolute_error: 2.0570 - val_loss: 2.9543 - val_mean_absolute_error: 1.2798
Epoch 56/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.1015 - mean_absolute_error: 2.0753 - val_loss: 2.7571 - val_mean_absolute_error: 1.2543
Epoch 57/1000
7/7 [==============================] - 0s 18ms/step - loss: 8.0593 - mean_absolute_error: 2.0492 - val_loss: 2.6849 - val_mean_absolute_error: 1.2606
Epoch 58/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.9592 - mean_absolute_error: 2.0692 - val_loss: 3.1558 - val_mean_absolute_error: 1.4066
Epoch 59/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.9292 - mean_absolute_error: 2.0245 - val_loss: 2.6209 - val_mean_absolute_error: 1.2645
Epoch 60/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.9834 - mean_absolute_error: 2.0509 - val_loss: 3.0405 - val_mean_absolute_error: 1.3803
Epoch 61/1000
7/7 [==============================] - 0s 23ms/step - loss: 8.1140 - mean_absolute_error: 2.1146 - val_loss: 2.9636 - val_mean_absolute_error: 1.3245
Epoch 62/1000
7/7 [==============================] - 0s 17ms/step - loss: 8.0367 - mean_absolute_error: 2.0719 - val_loss: 2.7207 - val_mean_absolute_error: 1.2574
Epoch 63/1000
7/7 [==============================] - 0s 17ms/step - loss: 8.8481 - mean_absolute_error: 2.1445 - val_loss: 3.4484 - val_mean_absolute_error: 1.4705
Epoch 64/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.6487 - mean_absolute_error: 2.0116 - val_loss: 2.5856 - val_mean_absolute_error: 1.2618
Epoch 65/1000
7/7 [==============================] - 0s 19ms/step - loss: 10.0826 - mean_absolute_error: 2.1529 - val_loss: 2.7362 - val_mean_absolute_error: 1.2553
Epoch 66/1000
7/7 [==============================] - 0s 18ms/step - loss: 8.2921 - mean_absolute_error: 2.1083 - val_loss: 3.1968 - val_mean_absolute_error: 1.3901
Epoch 67/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.5165 - mean_absolute_error: 2.1666 - val_loss: 2.9898 - val_mean_absolute_error: 1.3914
Epoch 68/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.7861 - mean_absolute_error: 1.9928 - val_loss: 2.7144 - val_mean_absolute_error: 1.2392
Epoch 69/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.8428 - mean_absolute_error: 2.0645 - val_loss: 3.0669 - val_mean_absolute_error: 1.3276
Epoch 70/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.4549 - mean_absolute_error: 1.9991 - val_loss: 3.1344 - val_mean_absolute_error: 1.3366
Epoch 71/1000
7/7 [==============================] - 0s 17ms/step - loss: 7.6113 - mean_absolute_error: 2.0119 - val_loss: 2.6552 - val_mean_absolute_error: 1.2498
Epoch 72/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.2583 - mean_absolute_error: 1.9664 - val_loss: 2.6118 - val_mean_absolute_error: 1.2365
Epoch 73/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.3354 - mean_absolute_error: 1.9656 - val_loss: 2.8790 - val_mean_absolute_error: 1.2790
Epoch 74/1000
7/7 [==============================] - 0s 17ms/step - loss: 7.2584 - mean_absolute_error: 1.9988 - val_loss: 2.8186 - val_mean_absolute_error: 1.2729
Epoch 75/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.1789 - mean_absolute_error: 1.9766 - val_loss: 2.5574 - val_mean_absolute_error: 1.2374
Epoch 76/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.3274 - mean_absolute_error: 1.9959 - val_loss: 2.6957 - val_mean_absolute_error: 1.1920
Epoch 77/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.4422 - mean_absolute_error: 2.0053 - val_loss: 2.9084 - val_mean_absolute_error: 1.2959
Epoch 78/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.3011 - mean_absolute_error: 1.9691 - val_loss: 2.5361 - val_mean_absolute_error: 1.1608
Epoch 79/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.0239 - mean_absolute_error: 1.9202 - val_loss: 2.7487 - val_mean_absolute_error: 1.2695
Epoch 80/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.1905 - mean_absolute_error: 1.9947 - val_loss: 2.9128 - val_mean_absolute_error: 1.3090
Epoch 81/1000
7/7 [==============================] - 0s 18ms/step - loss: 6.9760 - mean_absolute_error: 1.9562 - val_loss: 3.0182 - val_mean_absolute_error: 1.3158
Epoch 82/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.3691 - mean_absolute_error: 1.9768 - val_loss: 2.7013 - val_mean_absolute_error: 1.2745
Epoch 83/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.3182 - mean_absolute_error: 2.0302 - val_loss: 2.7599 - val_mean_absolute_error: 1.2691
Epoch 84/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.1830 - mean_absolute_error: 2.0185 - val_loss: 3.0987 - val_mean_absolute_error: 1.2791
Epoch 85/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.7322 - mean_absolute_error: 2.0385 - val_loss: 2.9574 - val_mean_absolute_error: 1.3227
Epoch 86/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.8041 - mean_absolute_error: 1.9016 - val_loss: 2.8028 - val_mean_absolute_error: 1.3106
Epoch 87/1000
7/7 [==============================] - 0s 18ms/step - loss: 6.5304 - mean_absolute_error: 1.8559 - val_loss: 2.6141 - val_mean_absolute_error: 1.2373
Epoch 88/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.6203 - mean_absolute_error: 1.8783 - val_loss: 2.5655 - val_mean_absolute_error: 1.2068
Epoch 89/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.3693 - mean_absolute_error: 1.8270 - val_loss: 2.9241 - val_mean_absolute_error: 1.3380
Epoch 90/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.4214 - mean_absolute_error: 1.8629 - val_loss: 2.7972 - val_mean_absolute_error: 1.2731
Epoch 91/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.1055 - mean_absolute_error: 1.8158 - val_loss: 2.6345 - val_mean_absolute_error: 1.2246
Epoch 92/1000
7/7 [==============================] - 0s 18ms/step - loss: 6.3525 - mean_absolute_error: 1.8423 - val_loss: 2.6128 - val_mean_absolute_error: 1.2525
Epoch 93/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.4716 - mean_absolute_error: 1.8672 - val_loss: 2.6659 - val_mean_absolute_error: 1.2497
Epoch 94/1000
7/7 [==============================] - 0s 18ms/step - loss: 6.0434 - mean_absolute_error: 1.8134 - val_loss: 2.5099 - val_mean_absolute_error: 1.1790
Epoch 95/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.3622 - mean_absolute_error: 1.8280 - val_loss: 3.0618 - val_mean_absolute_error: 1.3883
Epoch 96/1000
7/7 [==============================] - 0s 18ms/step - loss: 6.2480 - mean_absolute_error: 1.8282 - val_loss: 2.6334 - val_mean_absolute_error: 1.2544
Epoch 97/1000
7/7 [==============================] - 0s 31ms/step - loss: 6.2471 - mean_absolute_error: 1.8199 - val_loss: 2.5608 - val_mean_absolute_error: 1.2218
Epoch 98/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.0208 - mean_absolute_error: 1.8045 - val_loss: 3.0784 - val_mean_absolute_error: 1.3533
Epoch 99/1000
7/7 [==============================] - 0s 21ms/step - loss: 5.8965 - mean_absolute_error: 1.7710 - val_loss: 2.6663 - val_mean_absolute_error: 1.2560
Epoch 100/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.0237 - mean_absolute_error: 1.8016 - val_loss: 2.6347 - val_mean_absolute_error: 1.2782
Epoch 101/1000
7/7 [==============================] - 0s 21ms/step - loss: 5.7459 - mean_absolute_error: 1.7713 - val_loss: 2.8096 - val_mean_absolute_error: 1.2843
Epoch 102/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.7314 - mean_absolute_error: 1.7832 - val_loss: 2.7017 - val_mean_absolute_error: 1.2484
Epoch 103/1000
7/7 [==============================] - 0s 17ms/step - loss: 5.6315 - mean_absolute_error: 1.7391 - val_loss: 2.5796 - val_mean_absolute_error: 1.2028
Epoch 104/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.4770 - mean_absolute_error: 1.7105 - val_loss: 2.7879 - val_mean_absolute_error: 1.2770
Epoch 105/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.2666 - mean_absolute_error: 1.6739 - val_loss: 2.5124 - val_mean_absolute_error: 1.2259
Epoch 106/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.3419 - mean_absolute_error: 1.6906 - val_loss: 2.6408 - val_mean_absolute_error: 1.2418
Epoch 107/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.4645 - mean_absolute_error: 1.7092 - val_loss: 2.6619 - val_mean_absolute_error: 1.2681
Epoch 108/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.2645 - mean_absolute_error: 1.6658 - val_loss: 2.5538 - val_mean_absolute_error: 1.2263
Epoch 109/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.1953 - mean_absolute_error: 1.6646 - val_loss: 2.8876 - val_mean_absolute_error: 1.2989
Epoch 110/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.2212 - mean_absolute_error: 1.7139 - val_loss: 3.5707 - val_mean_absolute_error: 1.4868
Epoch 111/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.0561 - mean_absolute_error: 1.6732 - val_loss: 2.7440 - val_mean_absolute_error: 1.2651
Epoch 112/1000
7/7 [==============================] - 0s 28ms/step - loss: 5.3108 - mean_absolute_error: 1.7168 - val_loss: 2.9198 - val_mean_absolute_error: 1.3409
Epoch 113/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.1120 - mean_absolute_error: 1.6776 - val_loss: 2.6409 - val_mean_absolute_error: 1.3248
Epoch 114/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.8390 - mean_absolute_error: 1.6304 - val_loss: 2.7399 - val_mean_absolute_error: 1.2364
Epoch 115/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.8647 - mean_absolute_error: 1.6141 - val_loss: 2.5058 - val_mean_absolute_error: 1.2002
Epoch 116/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.6743 - mean_absolute_error: 1.6049 - val_loss: 2.8644 - val_mean_absolute_error: 1.3458
Epoch 117/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.5079 - mean_absolute_error: 1.5503 - val_loss: 2.5867 - val_mean_absolute_error: 1.2726
Epoch 118/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.7743 - mean_absolute_error: 1.5986 - val_loss: 3.0485 - val_mean_absolute_error: 1.3695
Epoch 119/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.5067 - mean_absolute_error: 1.5534 - val_loss: 2.9417 - val_mean_absolute_error: 1.3545
Epoch 120/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.6130 - mean_absolute_error: 1.6234 - val_loss: 2.7331 - val_mean_absolute_error: 1.2576
Epoch 121/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.3928 - mean_absolute_error: 1.5609 - val_loss: 2.7475 - val_mean_absolute_error: 1.2847
Epoch 122/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.7335 - mean_absolute_error: 1.6199 - val_loss: 2.8281 - val_mean_absolute_error: 1.3285
Epoch 123/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.8328 - mean_absolute_error: 1.6693 - val_loss: 3.0595 - val_mean_absolute_error: 1.4146
Epoch 124/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.8841 - mean_absolute_error: 1.6539 - val_loss: 2.9671 - val_mean_absolute_error: 1.3545
Epoch 125/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.5821 - mean_absolute_error: 1.7139 - val_loss: 2.7361 - val_mean_absolute_error: 1.3356
Epoch 126/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.2563 - mean_absolute_error: 1.5453 - val_loss: 2.7290 - val_mean_absolute_error: 1.3315
Epoch 127/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.4511 - mean_absolute_error: 1.6018 - val_loss: 2.5414 - val_mean_absolute_error: 1.2479
Epoch 128/1000
7/7 [==============================] - 0s 21ms/step - loss: 4.2449 - mean_absolute_error: 1.5200 - val_loss: 2.8443 - val_mean_absolute_error: 1.3718
Epoch 129/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.9002 - mean_absolute_error: 1.4500 - val_loss: 2.6487 - val_mean_absolute_error: 1.3504
Epoch 130/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.9238 - mean_absolute_error: 1.4532 - val_loss: 3.4625 - val_mean_absolute_error: 1.5169
Epoch 131/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.3851 - mean_absolute_error: 1.5031 - val_loss: 3.0585 - val_mean_absolute_error: 1.3277
Epoch 132/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.9786 - mean_absolute_error: 1.4928 - val_loss: 3.0635 - val_mean_absolute_error: 1.4219
Epoch 133/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.8175 - mean_absolute_error: 1.6401 - val_loss: 3.5255 - val_mean_absolute_error: 1.5531
Epoch 134/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.0081 - mean_absolute_error: 1.6865 - val_loss: 3.1250 - val_mean_absolute_error: 1.4212
Epoch 135/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.8461 - mean_absolute_error: 1.6288 - val_loss: 3.3158 - val_mean_absolute_error: 1.4351
Epoch 136/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.4165 - mean_absolute_error: 1.6146 - val_loss: 2.8824 - val_mean_absolute_error: 1.4571
Epoch 137/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.6930 - mean_absolute_error: 1.6529 - val_loss: 2.9420 - val_mean_absolute_error: 1.3630
Epoch 138/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.6792 - mean_absolute_error: 1.6081 - val_loss: 2.9556 - val_mean_absolute_error: 1.3646
Epoch 139/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.8883 - mean_absolute_error: 1.4678 - val_loss: 3.1207 - val_mean_absolute_error: 1.3740
Epoch 140/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.6868 - mean_absolute_error: 1.4205 - val_loss: 2.7020 - val_mean_absolute_error: 1.3695
Epoch 141/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.2650 - mean_absolute_error: 1.3219 - val_loss: 2.5934 - val_mean_absolute_error: 1.2731
Epoch 142/1000
7/7 [==============================] - 0s 22ms/step - loss: 3.3403 - mean_absolute_error: 1.3235 - val_loss: 2.9063 - val_mean_absolute_error: 1.3399
Epoch 143/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.2158 - mean_absolute_error: 1.3140 - val_loss: 2.6665 - val_mean_absolute_error: 1.3148
Epoch 144/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.0480 - mean_absolute_error: 1.2660 - val_loss: 2.8573 - val_mean_absolute_error: 1.3691
Epoch 145/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.9485 - mean_absolute_error: 1.2393 - val_loss: 3.0516 - val_mean_absolute_error: 1.3434
Epoch 146/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.9659 - mean_absolute_error: 1.2445 - val_loss: 2.9934 - val_mean_absolute_error: 1.3467
Epoch 147/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.0631 - mean_absolute_error: 1.3186 - val_loss: 2.6478 - val_mean_absolute_error: 1.3201
Epoch 148/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.1114 - mean_absolute_error: 1.2663 - val_loss: 3.6379 - val_mean_absolute_error: 1.5340
Epoch 149/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.0884 - mean_absolute_error: 1.3212 - val_loss: 2.8049 - val_mean_absolute_error: 1.4325
Epoch 150/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.8363 - mean_absolute_error: 1.2358 - val_loss: 3.3169 - val_mean_absolute_error: 1.4668
Epoch 151/1000
7/7 [==============================] - 0s 26ms/step - loss: 2.6729 - mean_absolute_error: 1.1838 - val_loss: 2.9302 - val_mean_absolute_error: 1.3998
Epoch 152/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.7446 - mean_absolute_error: 1.2324 - val_loss: 3.3977 - val_mean_absolute_error: 1.4141
Epoch 153/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.9506 - mean_absolute_error: 1.2876 - val_loss: 2.8441 - val_mean_absolute_error: 1.4383
Epoch 154/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.9484 - mean_absolute_error: 1.3083 - val_loss: 3.2088 - val_mean_absolute_error: 1.4183
Epoch 155/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.6058 - mean_absolute_error: 1.1778 - val_loss: 3.1120 - val_mean_absolute_error: 1.4261
Epoch 156/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5554 - mean_absolute_error: 1.1731 - val_loss: 3.0772 - val_mean_absolute_error: 1.4226
Epoch 157/1000
7/7 [==============================] - 0s 23ms/step - loss: 2.6185 - mean_absolute_error: 1.2043 - val_loss: 3.2104 - val_mean_absolute_error: 1.3592
Epoch 158/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5716 - mean_absolute_error: 1.2006 - val_loss: 2.7534 - val_mean_absolute_error: 1.3527
Epoch 159/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.2356 - mean_absolute_error: 1.0593 - val_loss: 3.0759 - val_mean_absolute_error: 1.3601
Epoch 160/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.2451 - mean_absolute_error: 1.0558 - val_loss: 2.9861 - val_mean_absolute_error: 1.3660
Epoch 161/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.2470 - mean_absolute_error: 1.0854 - val_loss: 3.2694 - val_mean_absolute_error: 1.4649
Epoch 162/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.2160 - mean_absolute_error: 1.0540 - val_loss: 3.0227 - val_mean_absolute_error: 1.4179
Epoch 163/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.1663 - mean_absolute_error: 1.0807 - val_loss: 3.1560 - val_mean_absolute_error: 1.3338
Epoch 164/1000
7/7 [==============================] - 0s 23ms/step - loss: 2.5163 - mean_absolute_error: 1.1319 - val_loss: 3.1576 - val_mean_absolute_error: 1.3188
Epoch 165/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.3733 - mean_absolute_error: 1.1207 - val_loss: 3.2860 - val_mean_absolute_error: 1.4393
Epoch 166/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.3526 - mean_absolute_error: 1.1499 - val_loss: 3.1255 - val_mean_absolute_error: 1.4440
Epoch 167/1000
7/7 [==============================] - 0s 30ms/step - loss: 2.1023 - mean_absolute_error: 1.0941 - val_loss: 3.2813 - val_mean_absolute_error: 1.4594
Epoch 168/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.0739 - mean_absolute_error: 1.0389 - val_loss: 2.9536 - val_mean_absolute_error: 1.3843
Epoch 169/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.9847 - mean_absolute_error: 1.0108 - val_loss: 3.2445 - val_mean_absolute_error: 1.4056
Epoch 170/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.9609 - mean_absolute_error: 1.0381 - val_loss: 3.3627 - val_mean_absolute_error: 1.4288
Epoch 171/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.1059 - mean_absolute_error: 1.0698 - val_loss: 3.1819 - val_mean_absolute_error: 1.3884
Epoch 172/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8485 - mean_absolute_error: 1.0134 - val_loss: 3.2004 - val_mean_absolute_error: 1.3965
Epoch 173/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8170 - mean_absolute_error: 0.9807 - val_loss: 3.2937 - val_mean_absolute_error: 1.4713
Epoch 174/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.7262 - mean_absolute_error: 0.9549 - val_loss: 3.0867 - val_mean_absolute_error: 1.3357
Epoch 175/1000
7/7 [==============================] - 0s 17ms/step - loss: 1.8498 - mean_absolute_error: 1.0233 - val_loss: 3.4628 - val_mean_absolute_error: 1.5061
Epoch 176/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9832 - mean_absolute_error: 1.0457 - val_loss: 3.8626 - val_mean_absolute_error: 1.5362
Epoch 177/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.0470 - mean_absolute_error: 1.0527 - val_loss: 3.2168 - val_mean_absolute_error: 1.4650
Epoch 178/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.9582 - mean_absolute_error: 1.0605 - val_loss: 3.0945 - val_mean_absolute_error: 1.3691
Epoch 179/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.9787 - mean_absolute_error: 1.0571 - val_loss: 3.9308 - val_mean_absolute_error: 1.5330
Epoch 180/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.3765 - mean_absolute_error: 1.1152 - val_loss: 3.4270 - val_mean_absolute_error: 1.4199
Epoch 181/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.3243 - mean_absolute_error: 1.0749 - val_loss: 3.9306 - val_mean_absolute_error: 1.5909
Epoch 182/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.1950 - mean_absolute_error: 1.0872 - val_loss: 4.0634 - val_mean_absolute_error: 1.5382
Epoch 183/1000
7/7 [==============================] - 0s 17ms/step - loss: 1.9320 - mean_absolute_error: 1.0380 - val_loss: 3.3372 - val_mean_absolute_error: 1.4572
Epoch 184/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.0822 - mean_absolute_error: 1.0543 - val_loss: 3.2259 - val_mean_absolute_error: 1.3681
Epoch 185/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.0612 - mean_absolute_error: 1.0590 - val_loss: 4.1611 - val_mean_absolute_error: 1.5214
Epoch 186/1000
7/7 [==============================] - 0s 27ms/step - loss: 2.3870 - mean_absolute_error: 1.1567 - val_loss: 3.1853 - val_mean_absolute_error: 1.4587
Epoch 187/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.9633 - mean_absolute_error: 1.0072 - val_loss: 3.7987 - val_mean_absolute_error: 1.5349
Epoch 188/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.2816 - mean_absolute_error: 1.1152 - val_loss: 3.5092 - val_mean_absolute_error: 1.4569
Epoch 189/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.2933 - mean_absolute_error: 1.1600 - val_loss: 3.6402 - val_mean_absolute_error: 1.5497
Epoch 190/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.7263 - mean_absolute_error: 0.9762 - val_loss: 2.9079 - val_mean_absolute_error: 1.2854
Epoch 191/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.4778 - mean_absolute_error: 1.1989 - val_loss: 3.5070 - val_mean_absolute_error: 1.5427
Epoch 192/1000
7/7 [==============================] - 0s 25ms/step - loss: 2.5423 - mean_absolute_error: 1.2261 - val_loss: 3.2530 - val_mean_absolute_error: 1.3632
Epoch 193/1000
7/7 [==============================] - 0s 23ms/step - loss: 2.8444 - mean_absolute_error: 1.2739 - val_loss: 3.4547 - val_mean_absolute_error: 1.4518
Epoch 194/1000
7/7 [==============================] - 0s 22ms/step - loss: 2.5850 - mean_absolute_error: 1.1658 - val_loss: 3.1097 - val_mean_absolute_error: 1.3284
Epoch 195/1000
7/7 [==============================] - 0s 22ms/step - loss: 2.1699 - mean_absolute_error: 1.0780 - val_loss: 4.0743 - val_mean_absolute_error: 1.5642
Epoch 196/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.9918 - mean_absolute_error: 1.0656 - val_loss: 2.9772 - val_mean_absolute_error: 1.4303
Epoch 197/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.9889 - mean_absolute_error: 1.0785 - val_loss: 3.6677 - val_mean_absolute_error: 1.4930
Epoch 198/1000
7/7 [==============================] - 0s 26ms/step - loss: 1.8051 - mean_absolute_error: 0.9426 - val_loss: 2.8729 - val_mean_absolute_error: 1.3068
Epoch 199/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.4327 - mean_absolute_error: 0.8728 - val_loss: 3.4649 - val_mean_absolute_error: 1.4668
Epoch 200/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.3610 - mean_absolute_error: 0.8444 - val_loss: 3.3743 - val_mean_absolute_error: 1.4088
Epoch 201/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.3004 - mean_absolute_error: 0.7976 - val_loss: 3.0542 - val_mean_absolute_error: 1.3672
Epoch 202/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.9670 - mean_absolute_error: 0.9862 - val_loss: 4.0389 - val_mean_absolute_error: 1.5477
Epoch 203/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.8449 - mean_absolute_error: 1.0414 - val_loss: 3.0936 - val_mean_absolute_error: 1.4228
Epoch 204/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.1892 - mean_absolute_error: 1.1050 - val_loss: 4.0795 - val_mean_absolute_error: 1.4896
Epoch 205/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.7306 - mean_absolute_error: 1.0073 - val_loss: 2.9650 - val_mean_absolute_error: 1.4173
Epoch 206/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5827 - mean_absolute_error: 0.9601 - val_loss: 3.5394 - val_mean_absolute_error: 1.4087
Epoch 207/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.3376 - mean_absolute_error: 0.8545 - val_loss: 3.2402 - val_mean_absolute_error: 1.4005
Epoch 208/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.3227 - mean_absolute_error: 0.8404 - val_loss: 3.1991 - val_mean_absolute_error: 1.3804
Epoch 209/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1226 - mean_absolute_error: 0.7620 - val_loss: 3.3614 - val_mean_absolute_error: 1.4791
Epoch 210/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0512 - mean_absolute_error: 0.7051 - val_loss: 3.2661 - val_mean_absolute_error: 1.4266
Epoch 211/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9860 - mean_absolute_error: 0.6917 - val_loss: 2.9803 - val_mean_absolute_error: 1.3470
Epoch 212/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9597 - mean_absolute_error: 0.6753 - val_loss: 3.4206 - val_mean_absolute_error: 1.3957
Epoch 213/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0006 - mean_absolute_error: 0.6974 - val_loss: 3.0160 - val_mean_absolute_error: 1.3522
Epoch 214/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9549 - mean_absolute_error: 0.6871 - val_loss: 3.2720 - val_mean_absolute_error: 1.4377
Epoch 215/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8999 - mean_absolute_error: 0.6240 - val_loss: 3.1905 - val_mean_absolute_error: 1.4043
Epoch 216/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9196 - mean_absolute_error: 0.6421 - val_loss: 3.0814 - val_mean_absolute_error: 1.3354
Epoch 217/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8838 - mean_absolute_error: 0.6559 - val_loss: 3.0420 - val_mean_absolute_error: 1.3921
Epoch 218/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.9385 - mean_absolute_error: 0.6788 - val_loss: 3.1166 - val_mean_absolute_error: 1.3884
Epoch 219/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9036 - mean_absolute_error: 0.6591 - val_loss: 3.2219 - val_mean_absolute_error: 1.3301
Epoch 220/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8314 - mean_absolute_error: 0.6439 - val_loss: 2.9704 - val_mean_absolute_error: 1.3610
Epoch 221/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0475 - mean_absolute_error: 0.7236 - val_loss: 3.6529 - val_mean_absolute_error: 1.4182
Epoch 222/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9258 - mean_absolute_error: 0.6721 - val_loss: 3.0645 - val_mean_absolute_error: 1.4575
Epoch 223/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9273 - mean_absolute_error: 0.7084 - val_loss: 3.3298 - val_mean_absolute_error: 1.4113
Epoch 224/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7786 - mean_absolute_error: 0.5930 - val_loss: 3.3645 - val_mean_absolute_error: 1.3865
Epoch 225/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8682 - mean_absolute_error: 0.6625 - val_loss: 3.1756 - val_mean_absolute_error: 1.2845
Epoch 226/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1242 - mean_absolute_error: 0.6996 - val_loss: 3.0216 - val_mean_absolute_error: 1.3093
Epoch 227/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9503 - mean_absolute_error: 0.9860 - val_loss: 3.8004 - val_mean_absolute_error: 1.6181
Epoch 228/1000
7/7 [==============================] - 0s 17ms/step - loss: 1.2533 - mean_absolute_error: 0.8230 - val_loss: 2.7178 - val_mean_absolute_error: 1.1750
Epoch 229/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2026 - mean_absolute_error: 0.7888 - val_loss: 2.9794 - val_mean_absolute_error: 1.3197
Epoch 230/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8946 - mean_absolute_error: 0.6436 - val_loss: 3.3697 - val_mean_absolute_error: 1.3564
Epoch 231/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8490 - mean_absolute_error: 0.6696 - val_loss: 3.0993 - val_mean_absolute_error: 1.4138
Epoch 232/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2411 - mean_absolute_error: 0.7049 - val_loss: 3.5743 - val_mean_absolute_error: 1.2925
Epoch 233/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.4592 - mean_absolute_error: 0.9095 - val_loss: 3.9699 - val_mean_absolute_error: 1.6923
Epoch 234/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.0832 - mean_absolute_error: 0.9738 - val_loss: 3.9061 - val_mean_absolute_error: 1.5197
Epoch 235/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.5686 - mean_absolute_error: 0.8964 - val_loss: 3.9686 - val_mean_absolute_error: 1.6302
Epoch 236/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.6275 - mean_absolute_error: 0.9596 - val_loss: 3.7583 - val_mean_absolute_error: 1.4150
Epoch 237/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9205 - mean_absolute_error: 0.9494 - val_loss: 3.3087 - val_mean_absolute_error: 1.4505
Epoch 238/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.4526 - mean_absolute_error: 0.8856 - val_loss: 3.4346 - val_mean_absolute_error: 1.4201
Epoch 239/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0112 - mean_absolute_error: 0.7315 - val_loss: 2.7433 - val_mean_absolute_error: 1.3078
Epoch 240/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1341 - mean_absolute_error: 0.7682 - val_loss: 2.8429 - val_mean_absolute_error: 1.3522
Epoch 241/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.9649 - mean_absolute_error: 0.6765 - val_loss: 3.8505 - val_mean_absolute_error: 1.4798
Epoch 242/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9151 - mean_absolute_error: 0.7161 - val_loss: 2.9502 - val_mean_absolute_error: 1.3618
Epoch 243/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8218 - mean_absolute_error: 0.6444 - val_loss: 3.1720 - val_mean_absolute_error: 1.4195
Epoch 244/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7936 - mean_absolute_error: 0.6073 - val_loss: 3.3709 - val_mean_absolute_error: 1.4282
Epoch 245/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.7422 - mean_absolute_error: 0.5853 - val_loss: 3.0387 - val_mean_absolute_error: 1.2949
Epoch 246/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.6333 - mean_absolute_error: 0.5490 - val_loss: 3.2653 - val_mean_absolute_error: 1.3228
Epoch 247/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.6737 - mean_absolute_error: 0.5532 - val_loss: 3.2722 - val_mean_absolute_error: 1.4295
Epoch 248/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.5771 - mean_absolute_error: 0.5508 - val_loss: 3.4738 - val_mean_absolute_error: 1.3643
Epoch 249/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.5274 - mean_absolute_error: 0.5079 - val_loss: 3.2447 - val_mean_absolute_error: 1.3689
Epoch 250/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.5325 - mean_absolute_error: 0.5091 - val_loss: 3.2137 - val_mean_absolute_error: 1.3599
Epoch 251/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.5178 - mean_absolute_error: 0.4702 - val_loss: 3.2854 - val_mean_absolute_error: 1.3379
Epoch 252/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.5867 - mean_absolute_error: 0.5113 - val_loss: 3.0880 - val_mean_absolute_error: 1.4201
Epoch 253/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.7679 - mean_absolute_error: 0.5949 - val_loss: 3.5416 - val_mean_absolute_error: 1.3267
Epoch 254/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.6227 - mean_absolute_error: 0.5294 - val_loss: 3.3771 - val_mean_absolute_error: 1.4497
Epoch 255/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5468 - mean_absolute_error: 0.5226 - val_loss: 2.9922 - val_mean_absolute_error: 1.2691
Epoch 256/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.5585 - mean_absolute_error: 0.5094 - val_loss: 3.5398 - val_mean_absolute_error: 1.4885
Epoch 257/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5017 - mean_absolute_error: 0.4806 - val_loss: 3.3498 - val_mean_absolute_error: 1.2869
Epoch 258/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7567 - mean_absolute_error: 0.5344 - val_loss: 3.3872 - val_mean_absolute_error: 1.3244
Epoch 259/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.6203 - mean_absolute_error: 0.4998 - val_loss: 3.3112 - val_mean_absolute_error: 1.3982
Epoch 260/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4858 - mean_absolute_error: 0.4752 - val_loss: 3.0888 - val_mean_absolute_error: 1.3719
Epoch 261/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.6231 - mean_absolute_error: 0.5180 - val_loss: 4.2465 - val_mean_absolute_error: 1.4853
Epoch 262/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.8466 - mean_absolute_error: 0.6445 - val_loss: 3.6284 - val_mean_absolute_error: 1.4528
Epoch 263/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.7000 - mean_absolute_error: 0.6062 - val_loss: 3.0870 - val_mean_absolute_error: 1.2932
Epoch 264/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.5390 - mean_absolute_error: 0.5124 - val_loss: 3.5302 - val_mean_absolute_error: 1.4152
Epoch 265/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.5309 - mean_absolute_error: 0.4900 - val_loss: 3.9173 - val_mean_absolute_error: 1.3984
Epoch 266/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.0243 - mean_absolute_error: 0.6419 - val_loss: 3.3662 - val_mean_absolute_error: 1.3236
Epoch 267/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.9626 - mean_absolute_error: 0.6676 - val_loss: 3.5836 - val_mean_absolute_error: 1.5812
Epoch 268/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.0945 - mean_absolute_error: 0.7256 - val_loss: 3.2049 - val_mean_absolute_error: 1.3222
Epoch 269/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6177 - mean_absolute_error: 0.5345 - val_loss: 3.8826 - val_mean_absolute_error: 1.4220
Epoch 270/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.6350 - mean_absolute_error: 0.5444 - val_loss: 2.6638 - val_mean_absolute_error: 1.2589
Epoch 271/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.6067 - mean_absolute_error: 0.5655 - val_loss: 3.5458 - val_mean_absolute_error: 1.4026
Epoch 272/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5799 - mean_absolute_error: 0.5576 - val_loss: 2.9358 - val_mean_absolute_error: 1.3582
Epoch 273/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7543 - mean_absolute_error: 0.5666 - val_loss: 3.4521 - val_mean_absolute_error: 1.2993
Epoch 274/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.4657 - mean_absolute_error: 0.6953 - val_loss: 3.3959 - val_mean_absolute_error: 1.3437
Epoch 275/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4855 - mean_absolute_error: 0.8819 - val_loss: 3.2553 - val_mean_absolute_error: 1.3267
Epoch 276/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.3821 - mean_absolute_error: 1.1470 - val_loss: 3.2409 - val_mean_absolute_error: 1.5310
Epoch 277/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0812 - mean_absolute_error: 0.7827 - val_loss: 4.4474 - val_mean_absolute_error: 1.4840
Epoch 278/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2295 - mean_absolute_error: 0.8177 - val_loss: 3.2408 - val_mean_absolute_error: 1.4114
Epoch 279/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7283 - mean_absolute_error: 0.6522 - val_loss: 3.4143 - val_mean_absolute_error: 1.3659
Epoch 280/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6615 - mean_absolute_error: 0.5925 - val_loss: 2.8128 - val_mean_absolute_error: 1.3225
Epoch 281/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4700 - mean_absolute_error: 0.4815 - val_loss: 3.4676 - val_mean_absolute_error: 1.4242
Epoch 282/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8232 - mean_absolute_error: 0.5513 - val_loss: 2.8044 - val_mean_absolute_error: 1.2116
Epoch 283/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5120 - mean_absolute_error: 0.5004 - val_loss: 3.1158 - val_mean_absolute_error: 1.4231
Epoch 284/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4679 - mean_absolute_error: 0.4835 - val_loss: 3.1366 - val_mean_absolute_error: 1.2060
Epoch 285/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3878 - mean_absolute_error: 0.4276 - val_loss: 3.0512 - val_mean_absolute_error: 1.3744
Epoch 286/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3070 - mean_absolute_error: 0.3578 - val_loss: 3.4720 - val_mean_absolute_error: 1.3255
Epoch 287/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3422 - mean_absolute_error: 0.3737 - val_loss: 3.1612 - val_mean_absolute_error: 1.3422
Epoch 288/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2873 - mean_absolute_error: 0.3459 - val_loss: 3.3597 - val_mean_absolute_error: 1.3008
Epoch 289/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3515 - mean_absolute_error: 0.3810 - val_loss: 3.0244 - val_mean_absolute_error: 1.3777
Epoch 290/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3528 - mean_absolute_error: 0.3853 - val_loss: 3.1509 - val_mean_absolute_error: 1.3122
Epoch 291/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3512 - mean_absolute_error: 0.3677 - val_loss: 3.6624 - val_mean_absolute_error: 1.4149
Epoch 292/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3055 - mean_absolute_error: 0.3683 - val_loss: 3.2907 - val_mean_absolute_error: 1.3404
Epoch 293/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3671 - mean_absolute_error: 0.3800 - val_loss: 3.4459 - val_mean_absolute_error: 1.4674
Epoch 294/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3756 - mean_absolute_error: 0.4166 - val_loss: 3.1500 - val_mean_absolute_error: 1.2844
Epoch 295/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3073 - mean_absolute_error: 0.3742 - val_loss: 3.3682 - val_mean_absolute_error: 1.4475
Epoch 296/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2852 - mean_absolute_error: 0.3511 - val_loss: 3.1928 - val_mean_absolute_error: 1.2892
Epoch 297/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2827 - mean_absolute_error: 0.3603 - val_loss: 3.0762 - val_mean_absolute_error: 1.3254
Epoch 298/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5654 - mean_absolute_error: 0.4549 - val_loss: 3.5268 - val_mean_absolute_error: 1.4963
Epoch 299/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5871 - mean_absolute_error: 0.5166 - val_loss: 3.1930 - val_mean_absolute_error: 1.2658
Epoch 300/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3645 - mean_absolute_error: 0.4175 - val_loss: 3.2736 - val_mean_absolute_error: 1.4084
Epoch 301/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2922 - mean_absolute_error: 0.3756 - val_loss: 3.3593 - val_mean_absolute_error: 1.3192
Epoch 302/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3047 - mean_absolute_error: 0.3551 - val_loss: 3.0560 - val_mean_absolute_error: 1.3866
Epoch 303/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3651 - mean_absolute_error: 0.3859 - val_loss: 3.1558 - val_mean_absolute_error: 1.3001
Epoch 304/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3178 - mean_absolute_error: 0.3613 - val_loss: 3.4144 - val_mean_absolute_error: 1.3190
Epoch 305/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4149 - mean_absolute_error: 0.4220 - val_loss: 3.1630 - val_mean_absolute_error: 1.4070
Epoch 306/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3826 - mean_absolute_error: 0.4360 - val_loss: 3.3990 - val_mean_absolute_error: 1.3187
Epoch 307/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4590 - mean_absolute_error: 0.4522 - val_loss: 3.5574 - val_mean_absolute_error: 1.5278
Epoch 308/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3956 - mean_absolute_error: 0.4368 - val_loss: 3.4328 - val_mean_absolute_error: 1.3094
Epoch 309/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.4145 - mean_absolute_error: 0.4378 - val_loss: 3.8386 - val_mean_absolute_error: 1.5051
Epoch 310/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4059 - mean_absolute_error: 0.4243 - val_loss: 3.2450 - val_mean_absolute_error: 1.3032
Epoch 311/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3659 - mean_absolute_error: 0.4148 - val_loss: 3.2839 - val_mean_absolute_error: 1.3776
Epoch 312/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3135 - mean_absolute_error: 0.3839 - val_loss: 3.2932 - val_mean_absolute_error: 1.3298
Epoch 313/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3164 - mean_absolute_error: 0.3708 - val_loss: 3.1125 - val_mean_absolute_error: 1.3587
Epoch 314/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2701 - mean_absolute_error: 0.3294 - val_loss: 3.2241 - val_mean_absolute_error: 1.2867
Epoch 315/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2289 - mean_absolute_error: 0.2891 - val_loss: 3.3248 - val_mean_absolute_error: 1.4094
Epoch 316/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1787 - mean_absolute_error: 0.2612 - val_loss: 3.2351 - val_mean_absolute_error: 1.2771
Epoch 317/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2493 - mean_absolute_error: 0.2973 - val_loss: 3.4122 - val_mean_absolute_error: 1.3565
Epoch 318/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.1901 - mean_absolute_error: 0.2682 - val_loss: 3.1955 - val_mean_absolute_error: 1.3812
Epoch 319/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1963 - mean_absolute_error: 0.2655 - val_loss: 3.3330 - val_mean_absolute_error: 1.3275
Epoch 320/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.1820 - mean_absolute_error: 0.2274 - val_loss: 3.3884 - val_mean_absolute_error: 1.3735
Epoch 321/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2185 - mean_absolute_error: 0.2595 - val_loss: 3.3765 - val_mean_absolute_error: 1.2880
Epoch 322/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1700 - mean_absolute_error: 0.2311 - val_loss: 3.3327 - val_mean_absolute_error: 1.3948
Epoch 323/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2063 - mean_absolute_error: 0.2390 - val_loss: 3.2502 - val_mean_absolute_error: 1.2725
Epoch 324/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1668 - mean_absolute_error: 0.2321 - val_loss: 3.2533 - val_mean_absolute_error: 1.3532
Epoch 325/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1928 - mean_absolute_error: 0.2388 - val_loss: 3.4159 - val_mean_absolute_error: 1.2935
Epoch 326/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1822 - mean_absolute_error: 0.2426 - val_loss: 3.3121 - val_mean_absolute_error: 1.3710
Epoch 327/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1818 - mean_absolute_error: 0.2572 - val_loss: 3.5793 - val_mean_absolute_error: 1.3508
Epoch 328/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2562 - mean_absolute_error: 0.3156 - val_loss: 3.1585 - val_mean_absolute_error: 1.3045
Epoch 329/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.2024 - mean_absolute_error: 0.2914 - val_loss: 3.3244 - val_mean_absolute_error: 1.3511
Epoch 330/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2180 - mean_absolute_error: 0.2809 - val_loss: 3.4065 - val_mean_absolute_error: 1.3219
Epoch 331/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2249 - mean_absolute_error: 0.2938 - val_loss: 3.4519 - val_mean_absolute_error: 1.3558
Epoch 332/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1780 - mean_absolute_error: 0.2460 - val_loss: 3.3433 - val_mean_absolute_error: 1.3319
Epoch 333/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1729 - mean_absolute_error: 0.2345 - val_loss: 3.5053 - val_mean_absolute_error: 1.3150
Epoch 334/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3370 - mean_absolute_error: 0.3220 - val_loss: 3.3289 - val_mean_absolute_error: 1.4258
Epoch 335/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3250 - mean_absolute_error: 0.3777 - val_loss: 3.4978 - val_mean_absolute_error: 1.2416
Epoch 336/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3727 - mean_absolute_error: 0.4180 - val_loss: 3.5591 - val_mean_absolute_error: 1.4753
Epoch 337/1000
7/7 [==============================] - 0s 36ms/step - loss: 0.4075 - mean_absolute_error: 0.4217 - val_loss: 3.6708 - val_mean_absolute_error: 1.2744
Epoch 338/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3687 - mean_absolute_error: 0.4412 - val_loss: 3.4399 - val_mean_absolute_error: 1.5119
Epoch 339/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3152 - mean_absolute_error: 0.3858 - val_loss: 3.7105 - val_mean_absolute_error: 1.3466
Epoch 340/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4614 - mean_absolute_error: 0.4111 - val_loss: 3.5411 - val_mean_absolute_error: 1.5301
Epoch 341/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8540 - mean_absolute_error: 0.5631 - val_loss: 3.7432 - val_mean_absolute_error: 1.3413
Epoch 342/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6393 - mean_absolute_error: 0.5617 - val_loss: 3.8273 - val_mean_absolute_error: 1.6093
Epoch 343/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4848 - mean_absolute_error: 0.4867 - val_loss: 3.2801 - val_mean_absolute_error: 1.2219
Epoch 344/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4747 - mean_absolute_error: 0.4882 - val_loss: 3.4828 - val_mean_absolute_error: 1.4789
Epoch 345/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3983 - mean_absolute_error: 0.4474 - val_loss: 4.1539 - val_mean_absolute_error: 1.3341
Epoch 346/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3629 - mean_absolute_error: 0.4033 - val_loss: 3.2597 - val_mean_absolute_error: 1.4481
Epoch 347/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2740 - mean_absolute_error: 0.3225 - val_loss: 3.1886 - val_mean_absolute_error: 1.2623
Epoch 348/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2987 - mean_absolute_error: 0.3377 - val_loss: 3.5222 - val_mean_absolute_error: 1.4450
Epoch 349/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2084 - mean_absolute_error: 0.2770 - val_loss: 3.2544 - val_mean_absolute_error: 1.2622
Epoch 350/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2643 - mean_absolute_error: 0.3268 - val_loss: 3.5665 - val_mean_absolute_error: 1.4673
Epoch 351/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2544 - mean_absolute_error: 0.3294 - val_loss: 3.8077 - val_mean_absolute_error: 1.3372
Epoch 352/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2988 - mean_absolute_error: 0.3443 - val_loss: 3.1070 - val_mean_absolute_error: 1.3451
Epoch 353/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2308 - mean_absolute_error: 0.3034 - val_loss: 3.4008 - val_mean_absolute_error: 1.2469
Epoch 354/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2215 - mean_absolute_error: 0.2947 - val_loss: 3.4396 - val_mean_absolute_error: 1.3936
Epoch 355/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2110 - mean_absolute_error: 0.2780 - val_loss: 3.2983 - val_mean_absolute_error: 1.3836
Epoch 356/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4320 - mean_absolute_error: 0.3647 - val_loss: 3.8123 - val_mean_absolute_error: 1.3432
Epoch 357/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4047 - mean_absolute_error: 0.4096 - val_loss: 3.8968 - val_mean_absolute_error: 1.5930
Epoch 358/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2906 - mean_absolute_error: 0.3559 - val_loss: 3.3000 - val_mean_absolute_error: 1.2577
Epoch 359/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2801 - mean_absolute_error: 0.3722 - val_loss: 3.4730 - val_mean_absolute_error: 1.4411
Epoch 360/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2650 - mean_absolute_error: 0.3534 - val_loss: 3.7021 - val_mean_absolute_error: 1.3048
Epoch 361/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2479 - mean_absolute_error: 0.3356 - val_loss: 3.3354 - val_mean_absolute_error: 1.4299
Epoch 362/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2830 - mean_absolute_error: 0.3670 - val_loss: 3.3734 - val_mean_absolute_error: 1.2980
Epoch 363/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3069 - mean_absolute_error: 0.3759 - val_loss: 3.4944 - val_mean_absolute_error: 1.4246
Epoch 364/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2559 - mean_absolute_error: 0.3185 - val_loss: 3.3389 - val_mean_absolute_error: 1.2923
Epoch 365/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2019 - mean_absolute_error: 0.2744 - val_loss: 3.4349 - val_mean_absolute_error: 1.3615
Epoch 366/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1940 - mean_absolute_error: 0.2573 - val_loss: 3.6467 - val_mean_absolute_error: 1.4147
Epoch 367/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2561 - mean_absolute_error: 0.3411 - val_loss: 3.4052 - val_mean_absolute_error: 1.3655
Epoch 368/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4651 - mean_absolute_error: 0.3603 - val_loss: 3.5093 - val_mean_absolute_error: 1.4100
Epoch 369/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.3867 - mean_absolute_error: 0.3750 - val_loss: 3.3349 - val_mean_absolute_error: 1.2826
Epoch 370/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.3276 - mean_absolute_error: 0.3693 - val_loss: 4.3609 - val_mean_absolute_error: 1.5931
Epoch 371/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2797 - mean_absolute_error: 0.3640 - val_loss: 4.1271 - val_mean_absolute_error: 1.4678
Epoch 372/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2546 - mean_absolute_error: 0.3076 - val_loss: 3.5603 - val_mean_absolute_error: 1.4553
Epoch 373/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1831 - mean_absolute_error: 0.2472 - val_loss: 3.6370 - val_mean_absolute_error: 1.3686
Epoch 374/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1600 - mean_absolute_error: 0.2287 - val_loss: 3.5923 - val_mean_absolute_error: 1.4289
Epoch 375/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1361 - mean_absolute_error: 0.1928 - val_loss: 3.5484 - val_mean_absolute_error: 1.3780
Epoch 376/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1319 - mean_absolute_error: 0.1800 - val_loss: 3.6952 - val_mean_absolute_error: 1.4327
Epoch 377/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1414 - mean_absolute_error: 0.1668 - val_loss: 3.6839 - val_mean_absolute_error: 1.4014
Epoch 378/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1436 - mean_absolute_error: 0.1892 - val_loss: 3.4876 - val_mean_absolute_error: 1.4150
Epoch 379/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1405 - mean_absolute_error: 0.1655 - val_loss: 3.6525 - val_mean_absolute_error: 1.3921
Epoch 380/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1321 - mean_absolute_error: 0.1669 - val_loss: 3.6699 - val_mean_absolute_error: 1.4641
Epoch 381/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1222 - mean_absolute_error: 0.1915 - val_loss: 3.5112 - val_mean_absolute_error: 1.3573
Epoch 382/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1556 - mean_absolute_error: 0.1917 - val_loss: 3.7214 - val_mean_absolute_error: 1.4551
Epoch 383/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4454 - mean_absolute_error: 0.3117 - val_loss: 3.7994 - val_mean_absolute_error: 1.3419
Epoch 384/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2855 - mean_absolute_error: 0.3187 - val_loss: 3.6856 - val_mean_absolute_error: 1.5050
Epoch 385/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.2548 - mean_absolute_error: 0.3208 - val_loss: 3.3969 - val_mean_absolute_error: 1.3079
Epoch 386/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2492 - mean_absolute_error: 0.3131 - val_loss: 3.5775 - val_mean_absolute_error: 1.3903
Epoch 387/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1834 - mean_absolute_error: 0.2653 - val_loss: 3.7488 - val_mean_absolute_error: 1.3242
Epoch 388/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2165 - mean_absolute_error: 0.2795 - val_loss: 3.3123 - val_mean_absolute_error: 1.4014
Epoch 389/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2327 - mean_absolute_error: 0.3196 - val_loss: 3.5658 - val_mean_absolute_error: 1.3864
Epoch 390/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1607 - mean_absolute_error: 0.2427 - val_loss: 3.6065 - val_mean_absolute_error: 1.3775
Epoch 391/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1581 - mean_absolute_error: 0.2444 - val_loss: 3.5514 - val_mean_absolute_error: 1.4551
Epoch 392/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2026 - mean_absolute_error: 0.2568 - val_loss: 3.6090 - val_mean_absolute_error: 1.3248
Epoch 393/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2418 - mean_absolute_error: 0.3228 - val_loss: 3.6334 - val_mean_absolute_error: 1.5182
Epoch 394/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2413 - mean_absolute_error: 0.3281 - val_loss: 3.8879 - val_mean_absolute_error: 1.3452
Epoch 395/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2755 - mean_absolute_error: 0.3723 - val_loss: 3.5265 - val_mean_absolute_error: 1.4561
Epoch 396/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2503 - mean_absolute_error: 0.3261 - val_loss: 3.6591 - val_mean_absolute_error: 1.3409
Epoch 397/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2533 - mean_absolute_error: 0.3250 - val_loss: 3.4209 - val_mean_absolute_error: 1.4138
Epoch 398/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2015 - mean_absolute_error: 0.2763 - val_loss: 3.6528 - val_mean_absolute_error: 1.4158
Epoch 399/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2190 - mean_absolute_error: 0.2846 - val_loss: 3.5076 - val_mean_absolute_error: 1.3329
Epoch 400/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1500 - mean_absolute_error: 0.2230 - val_loss: 3.3326 - val_mean_absolute_error: 1.3823
Epoch 401/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2106 - mean_absolute_error: 0.2335 - val_loss: 3.5012 - val_mean_absolute_error: 1.3611
Epoch 402/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1514 - mean_absolute_error: 0.2174 - val_loss: 3.5702 - val_mean_absolute_error: 1.3396
Epoch 403/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1915 - mean_absolute_error: 0.2460 - val_loss: 3.5956 - val_mean_absolute_error: 1.4796
Epoch 404/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1775 - mean_absolute_error: 0.2682 - val_loss: 3.5325 - val_mean_absolute_error: 1.3202
Epoch 405/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2209 - mean_absolute_error: 0.2765 - val_loss: 3.6674 - val_mean_absolute_error: 1.4368
Epoch 406/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3061 - mean_absolute_error: 0.3183 - val_loss: 3.4252 - val_mean_absolute_error: 1.3203
Epoch 407/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2242 - mean_absolute_error: 0.3256 - val_loss: 3.3624 - val_mean_absolute_error: 1.3598
Epoch 408/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2144 - mean_absolute_error: 0.2902 - val_loss: 3.8687 - val_mean_absolute_error: 1.3986
Epoch 409/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5272 - mean_absolute_error: 0.4257 - val_loss: 3.8712 - val_mean_absolute_error: 1.3907
Epoch 410/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4751 - mean_absolute_error: 0.4417 - val_loss: 3.2661 - val_mean_absolute_error: 1.3534
Epoch 411/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3495 - mean_absolute_error: 0.3720 - val_loss: 3.6026 - val_mean_absolute_error: 1.4106
Epoch 412/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3568 - mean_absolute_error: 0.3986 - val_loss: 3.9876 - val_mean_absolute_error: 1.4740
Epoch 413/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.4054 - mean_absolute_error: 0.4528 - val_loss: 3.1906 - val_mean_absolute_error: 1.2832
Epoch 414/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4435 - mean_absolute_error: 0.4917 - val_loss: 3.5668 - val_mean_absolute_error: 1.4228
Epoch 415/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4881 - mean_absolute_error: 0.4965 - val_loss: 3.5896 - val_mean_absolute_error: 1.3983
Epoch 416/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.5191 - mean_absolute_error: 0.5311 - val_loss: 4.1064 - val_mean_absolute_error: 1.5517
Epoch 417/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5794 - mean_absolute_error: 0.5300 - val_loss: 3.0130 - val_mean_absolute_error: 1.3036
Epoch 418/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.6231 - mean_absolute_error: 0.5629 - val_loss: 3.3530 - val_mean_absolute_error: 1.4606
Epoch 419/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.6124 - mean_absolute_error: 0.5431 - val_loss: 4.4028 - val_mean_absolute_error: 1.5717
Epoch 420/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0199 - mean_absolute_error: 0.7049 - val_loss: 3.6788 - val_mean_absolute_error: 1.3959
Epoch 421/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.8945 - mean_absolute_error: 0.7200 - val_loss: 3.6946 - val_mean_absolute_error: 1.5524
Epoch 422/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7488 - mean_absolute_error: 0.6792 - val_loss: 3.5182 - val_mean_absolute_error: 1.3496
Epoch 423/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5926 - mean_absolute_error: 0.5864 - val_loss: 3.1489 - val_mean_absolute_error: 1.3469
Epoch 424/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5717 - mean_absolute_error: 0.5342 - val_loss: 3.0093 - val_mean_absolute_error: 1.2077
Epoch 425/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4879 - mean_absolute_error: 0.4962 - val_loss: 3.1260 - val_mean_absolute_error: 1.3089
Epoch 426/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3670 - mean_absolute_error: 0.4100 - val_loss: 3.2790 - val_mean_absolute_error: 1.4030
Epoch 427/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.2380 - mean_absolute_error: 0.3350 - val_loss: 3.2924 - val_mean_absolute_error: 1.2941
Epoch 428/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1974 - mean_absolute_error: 0.2933 - val_loss: 3.4041 - val_mean_absolute_error: 1.3287
Epoch 429/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2999 - mean_absolute_error: 0.3052 - val_loss: 3.1237 - val_mean_absolute_error: 1.3919
Epoch 430/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2997 - mean_absolute_error: 0.3204 - val_loss: 3.6484 - val_mean_absolute_error: 1.2821
Epoch 431/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2438 - mean_absolute_error: 0.3284 - val_loss: 3.3358 - val_mean_absolute_error: 1.4534
Epoch 432/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2175 - mean_absolute_error: 0.2988 - val_loss: 3.1340 - val_mean_absolute_error: 1.2701
Epoch 433/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1683 - mean_absolute_error: 0.2590 - val_loss: 3.4556 - val_mean_absolute_error: 1.4458
Epoch 434/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1841 - mean_absolute_error: 0.2650 - val_loss: 3.2800 - val_mean_absolute_error: 1.2973
Epoch 435/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1567 - mean_absolute_error: 0.2367 - val_loss: 3.3576 - val_mean_absolute_error: 1.3708
Epoch 436/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1545 - mean_absolute_error: 0.2363 - val_loss: 3.3266 - val_mean_absolute_error: 1.2836
Epoch 437/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1467 - mean_absolute_error: 0.2282 - val_loss: 3.3110 - val_mean_absolute_error: 1.3656
Epoch 438/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1271 - mean_absolute_error: 0.1983 - val_loss: 3.2391 - val_mean_absolute_error: 1.3367
Epoch 439/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1241 - mean_absolute_error: 0.1760 - val_loss: 3.2784 - val_mean_absolute_error: 1.3196
Epoch 440/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1312 - mean_absolute_error: 0.1567 - val_loss: 3.3777 - val_mean_absolute_error: 1.3253
Epoch 441/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1196 - mean_absolute_error: 0.1581 - val_loss: 3.2797 - val_mean_absolute_error: 1.3728
Epoch 442/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1203 - mean_absolute_error: 0.1513 - val_loss: 3.2459 - val_mean_absolute_error: 1.3235
Epoch 443/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1045 - mean_absolute_error: 0.1431 - val_loss: 3.4067 - val_mean_absolute_error: 1.3475
Epoch 444/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0976 - mean_absolute_error: 0.1372 - val_loss: 3.2195 - val_mean_absolute_error: 1.3421
Epoch 445/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1406 - mean_absolute_error: 0.1622 - val_loss: 3.3094 - val_mean_absolute_error: 1.3251
Epoch 446/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1817 - mean_absolute_error: 0.1709 - val_loss: 3.3160 - val_mean_absolute_error: 1.3301
Epoch 447/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1885 - mean_absolute_error: 0.2127 - val_loss: 3.4864 - val_mean_absolute_error: 1.4209
Epoch 448/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1390 - mean_absolute_error: 0.2170 - val_loss: 3.3763 - val_mean_absolute_error: 1.3117
Epoch 449/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1679 - mean_absolute_error: 0.2106 - val_loss: 3.1762 - val_mean_absolute_error: 1.3351
Epoch 450/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1785 - mean_absolute_error: 0.2571 - val_loss: 3.4782 - val_mean_absolute_error: 1.3218
Epoch 451/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1453 - mean_absolute_error: 0.2147 - val_loss: 3.2667 - val_mean_absolute_error: 1.2980
Epoch 452/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1303 - mean_absolute_error: 0.2194 - val_loss: 3.3784 - val_mean_absolute_error: 1.4095
Epoch 453/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1458 - mean_absolute_error: 0.2391 - val_loss: 3.4816 - val_mean_absolute_error: 1.3250
Epoch 454/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.1768 - mean_absolute_error: 0.2490 - val_loss: 3.4560 - val_mean_absolute_error: 1.3619
Epoch 455/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2286 - mean_absolute_error: 0.2684 - val_loss: 3.2377 - val_mean_absolute_error: 1.3086
Epoch 456/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2353 - mean_absolute_error: 0.3216 - val_loss: 3.4430 - val_mean_absolute_error: 1.3927
Epoch 457/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3462 - mean_absolute_error: 0.3228 - val_loss: 3.6668 - val_mean_absolute_error: 1.3998
Epoch 458/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2204 - mean_absolute_error: 0.2794 - val_loss: 3.4074 - val_mean_absolute_error: 1.4153
Epoch 459/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2249 - mean_absolute_error: 0.3057 - val_loss: 3.3388 - val_mean_absolute_error: 1.3278
Epoch 460/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2044 - mean_absolute_error: 0.2762 - val_loss: 3.4079 - val_mean_absolute_error: 1.3368
Epoch 461/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1855 - mean_absolute_error: 0.2461 - val_loss: 3.3956 - val_mean_absolute_error: 1.3638
Epoch 462/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1231 - mean_absolute_error: 0.2163 - val_loss: 3.4553 - val_mean_absolute_error: 1.3295
Epoch 463/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1759 - mean_absolute_error: 0.2675 - val_loss: 3.1581 - val_mean_absolute_error: 1.3253
Epoch 464/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2236 - mean_absolute_error: 0.2685 - val_loss: 3.1429 - val_mean_absolute_error: 1.3898
Epoch 465/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3324 - mean_absolute_error: 0.3800 - val_loss: 3.3550 - val_mean_absolute_error: 1.2648
Epoch 466/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4056 - mean_absolute_error: 0.3816 - val_loss: 3.9454 - val_mean_absolute_error: 1.5928
Epoch 467/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4397 - mean_absolute_error: 0.4159 - val_loss: 3.8356 - val_mean_absolute_error: 1.2762
Epoch 468/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4857 - mean_absolute_error: 0.4867 - val_loss: 3.7770 - val_mean_absolute_error: 1.6164
Epoch 469/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.8402 - mean_absolute_error: 0.6484 - val_loss: 3.9139 - val_mean_absolute_error: 1.2941
Epoch 470/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.8110 - mean_absolute_error: 0.6437 - val_loss: 3.0885 - val_mean_absolute_error: 1.3878
Epoch 471/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.6465 - mean_absolute_error: 0.5585 - val_loss: 3.1927 - val_mean_absolute_error: 1.2854
Epoch 472/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4918 - mean_absolute_error: 0.4696 - val_loss: 3.4349 - val_mean_absolute_error: 1.4221
Epoch 473/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.5626 - mean_absolute_error: 0.5357 - val_loss: 4.0745 - val_mean_absolute_error: 1.4450
Epoch 474/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4607 - mean_absolute_error: 0.5001 - val_loss: 3.6469 - val_mean_absolute_error: 1.4463
Epoch 475/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.4403 - mean_absolute_error: 0.4805 - val_loss: 3.0439 - val_mean_absolute_error: 1.4435
Epoch 476/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.4012 - mean_absolute_error: 0.4654 - val_loss: 3.8278 - val_mean_absolute_error: 1.4220
Epoch 477/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.4162 - mean_absolute_error: 0.4422 - val_loss: 3.1652 - val_mean_absolute_error: 1.2978
Epoch 478/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3889 - mean_absolute_error: 0.4203 - val_loss: 3.4086 - val_mean_absolute_error: 1.3829
Epoch 479/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.3275 - mean_absolute_error: 0.3989 - val_loss: 3.3736 - val_mean_absolute_error: 1.3810
Epoch 480/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2410 - mean_absolute_error: 0.3488 - val_loss: 3.4586 - val_mean_absolute_error: 1.3996
Epoch 481/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.2599 - mean_absolute_error: 0.3179 - val_loss: 3.4735 - val_mean_absolute_error: 1.3406
Epoch 482/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.3395 - mean_absolute_error: 0.3846 - val_loss: 3.2302 - val_mean_absolute_error: 1.4016
Epoch 483/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.2744 - mean_absolute_error: 0.3478 - val_loss: 3.1494 - val_mean_absolute_error: 1.2603
Epoch 484/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.3121 - mean_absolute_error: 0.3771 - val_loss: 3.7791 - val_mean_absolute_error: 1.3546
Epoch 485/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.2825 - mean_absolute_error: 0.3487 - val_loss: 3.8242 - val_mean_absolute_error: 1.4670
Epoch 486/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.8285 - mean_absolute_error: 0.5491 - val_loss: 2.9566 - val_mean_absolute_error: 1.3197
Epoch 487/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.8310 - mean_absolute_error: 0.6876 - val_loss: 3.8287 - val_mean_absolute_error: 1.4982
Epoch 488/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.8107 - mean_absolute_error: 0.6039 - val_loss: 4.1336 - val_mean_absolute_error: 1.4140
Epoch 489/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.6619 - mean_absolute_error: 0.5943 - val_loss: 3.4367 - val_mean_absolute_error: 1.4711
Epoch 490/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.6059 - mean_absolute_error: 0.5861 - val_loss: 3.2322 - val_mean_absolute_error: 1.3394
Epoch 491/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3623 - mean_absolute_error: 0.4519 - val_loss: 3.2331 - val_mean_absolute_error: 1.3223
Epoch 492/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4105 - mean_absolute_error: 0.4263 - val_loss: 2.9743 - val_mean_absolute_error: 1.3488
Epoch 493/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3193 - mean_absolute_error: 0.4004 - val_loss: 3.3818 - val_mean_absolute_error: 1.3099
Epoch 494/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2418 - mean_absolute_error: 0.3388 - val_loss: 3.1441 - val_mean_absolute_error: 1.3155
Epoch 495/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1961 - mean_absolute_error: 0.2908 - val_loss: 3.1732 - val_mean_absolute_error: 1.3556
Epoch 496/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1890 - mean_absolute_error: 0.2825 - val_loss: 3.2973 - val_mean_absolute_error: 1.3832
Epoch 497/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1450 - mean_absolute_error: 0.2387 - val_loss: 3.4709 - val_mean_absolute_error: 1.3361
Epoch 498/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1544 - mean_absolute_error: 0.2234 - val_loss: 3.3538 - val_mean_absolute_error: 1.3618
Epoch 499/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1203 - mean_absolute_error: 0.1906 - val_loss: 3.2486 - val_mean_absolute_error: 1.3493
Epoch 500/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1409 - mean_absolute_error: 0.1810 - val_loss: 3.3459 - val_mean_absolute_error: 1.2996
Epoch 501/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1967 - mean_absolute_error: 0.2184 - val_loss: 3.3873 - val_mean_absolute_error: 1.3835
Epoch 502/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2529 - mean_absolute_error: 0.3081 - val_loss: 3.4559 - val_mean_absolute_error: 1.3056
Epoch 503/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4136 - mean_absolute_error: 0.3948 - val_loss: 3.4002 - val_mean_absolute_error: 1.4311
Epoch 504/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3038 - mean_absolute_error: 0.3888 - val_loss: 3.2934 - val_mean_absolute_error: 1.2698
Epoch 505/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2447 - mean_absolute_error: 0.3178 - val_loss: 3.1446 - val_mean_absolute_error: 1.3595
Epoch 506/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1823 - mean_absolute_error: 0.2711 - val_loss: 3.2414 - val_mean_absolute_error: 1.3413
Epoch 507/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1283 - mean_absolute_error: 0.2201 - val_loss: 3.4141 - val_mean_absolute_error: 1.3733
Epoch 508/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1572 - mean_absolute_error: 0.1787 - val_loss: 3.3249 - val_mean_absolute_error: 1.3334
Epoch 509/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1160 - mean_absolute_error: 0.1625 - val_loss: 3.2523 - val_mean_absolute_error: 1.3076
Epoch 510/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1316 - mean_absolute_error: 0.1959 - val_loss: 3.3583 - val_mean_absolute_error: 1.4181
Epoch 511/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3644 - mean_absolute_error: 0.3353 - val_loss: 3.4640 - val_mean_absolute_error: 1.2781
Epoch 512/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2778 - mean_absolute_error: 0.3440 - val_loss: 3.5367 - val_mean_absolute_error: 1.4991
Epoch 513/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1905 - mean_absolute_error: 0.3074 - val_loss: 3.3642 - val_mean_absolute_error: 1.2818
Epoch 514/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1934 - mean_absolute_error: 0.2693 - val_loss: 3.3443 - val_mean_absolute_error: 1.4116
Epoch 515/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1396 - mean_absolute_error: 0.2535 - val_loss: 3.3525 - val_mean_absolute_error: 1.2442
Epoch 516/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1714 - mean_absolute_error: 0.2846 - val_loss: 3.3972 - val_mean_absolute_error: 1.3980
Epoch 517/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1650 - mean_absolute_error: 0.2487 - val_loss: 3.2375 - val_mean_absolute_error: 1.3271
Epoch 518/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1771 - mean_absolute_error: 0.2791 - val_loss: 3.4860 - val_mean_absolute_error: 1.3781
Epoch 519/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1257 - mean_absolute_error: 0.2219 - val_loss: 3.3729 - val_mean_absolute_error: 1.3164
Epoch 520/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1321 - mean_absolute_error: 0.2152 - val_loss: 3.3033 - val_mean_absolute_error: 1.3714
Epoch 521/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2257 - mean_absolute_error: 0.2582 - val_loss: 3.4965 - val_mean_absolute_error: 1.3568
Epoch 522/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1395 - mean_absolute_error: 0.2403 - val_loss: 3.2492 - val_mean_absolute_error: 1.3801
Epoch 523/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.1803 - mean_absolute_error: 0.2459 - val_loss: 3.2633 - val_mean_absolute_error: 1.3205
Epoch 524/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1825 - mean_absolute_error: 0.2568 - val_loss: 3.3585 - val_mean_absolute_error: 1.2534
Epoch 525/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1714 - mean_absolute_error: 0.2406 - val_loss: 3.2533 - val_mean_absolute_error: 1.4137
Epoch 526/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1886 - mean_absolute_error: 0.2445 - val_loss: 3.4337 - val_mean_absolute_error: 1.3178
Epoch 527/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2050 - mean_absolute_error: 0.2563 - val_loss: 3.5004 - val_mean_absolute_error: 1.4498
Epoch 528/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.3155 - mean_absolute_error: 0.3219 - val_loss: 3.7045 - val_mean_absolute_error: 1.3216
Epoch 529/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2927 - mean_absolute_error: 0.3918 - val_loss: 3.5782 - val_mean_absolute_error: 1.5016
Epoch 530/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2857 - mean_absolute_error: 0.3838 - val_loss: 3.5878 - val_mean_absolute_error: 1.2802
Epoch 531/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3447 - mean_absolute_error: 0.3768 - val_loss: 3.8511 - val_mean_absolute_error: 1.5775
Epoch 532/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2945 - mean_absolute_error: 0.3845 - val_loss: 3.2761 - val_mean_absolute_error: 1.3040
Epoch 533/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2914 - mean_absolute_error: 0.3738 - val_loss: 3.7027 - val_mean_absolute_error: 1.5133
Epoch 534/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6078 - mean_absolute_error: 0.5123 - val_loss: 3.6389 - val_mean_absolute_error: 1.3616
Epoch 535/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.7296 - mean_absolute_error: 0.5615 - val_loss: 3.1468 - val_mean_absolute_error: 1.3693
Epoch 536/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.7217 - mean_absolute_error: 0.5187 - val_loss: 3.8391 - val_mean_absolute_error: 1.3729
Epoch 537/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7446 - mean_absolute_error: 0.5854 - val_loss: 3.5842 - val_mean_absolute_error: 1.4029
Epoch 538/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6917 - mean_absolute_error: 0.5342 - val_loss: 3.0033 - val_mean_absolute_error: 1.3251
Epoch 539/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6302 - mean_absolute_error: 0.5062 - val_loss: 3.5936 - val_mean_absolute_error: 1.4395
Epoch 540/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.4923 - mean_absolute_error: 0.4434 - val_loss: 3.3690 - val_mean_absolute_error: 1.3693
Epoch 541/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4148 - mean_absolute_error: 0.4136 - val_loss: 3.2933 - val_mean_absolute_error: 1.2711
Epoch 542/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4388 - mean_absolute_error: 0.4174 - val_loss: 3.0766 - val_mean_absolute_error: 1.3666
Epoch 543/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6401 - mean_absolute_error: 0.5684 - val_loss: 4.1018 - val_mean_absolute_error: 1.5009
Epoch 544/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8197 - mean_absolute_error: 0.6657 - val_loss: 3.1879 - val_mean_absolute_error: 1.4930
Epoch 545/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6788 - mean_absolute_error: 0.5800 - val_loss: 3.7442 - val_mean_absolute_error: 1.3997
Epoch 546/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3934 - mean_absolute_error: 0.4713 - val_loss: 3.7799 - val_mean_absolute_error: 1.3705
Epoch 547/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4091 - mean_absolute_error: 0.4060 - val_loss: 3.5570 - val_mean_absolute_error: 1.4851
Epoch 548/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2910 - mean_absolute_error: 0.3651 - val_loss: 3.3152 - val_mean_absolute_error: 1.3007
Epoch 549/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2661 - mean_absolute_error: 0.3636 - val_loss: 2.8988 - val_mean_absolute_error: 1.3240
Epoch 550/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3190 - mean_absolute_error: 0.3756 - val_loss: 3.5017 - val_mean_absolute_error: 1.3815
Epoch 551/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3762 - mean_absolute_error: 0.3596 - val_loss: 3.3906 - val_mean_absolute_error: 1.3525
Epoch 552/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2060 - mean_absolute_error: 0.3006 - val_loss: 3.3056 - val_mean_absolute_error: 1.4641
Epoch 553/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1870 - mean_absolute_error: 0.2672 - val_loss: 3.6817 - val_mean_absolute_error: 1.2935
Epoch 554/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3508 - mean_absolute_error: 0.3565 - val_loss: 3.4398 - val_mean_absolute_error: 1.4739
Epoch 555/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4157 - mean_absolute_error: 0.4052 - val_loss: 2.9965 - val_mean_absolute_error: 1.2074
Epoch 556/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3836 - mean_absolute_error: 0.3872 - val_loss: 3.6757 - val_mean_absolute_error: 1.4382
Epoch 557/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3343 - mean_absolute_error: 0.4091 - val_loss: 3.3522 - val_mean_absolute_error: 1.2911
Epoch 558/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2998 - mean_absolute_error: 0.3661 - val_loss: 3.4871 - val_mean_absolute_error: 1.4566
Epoch 559/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2082 - mean_absolute_error: 0.3252 - val_loss: 3.2661 - val_mean_absolute_error: 1.3270
Epoch 560/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2100 - mean_absolute_error: 0.3068 - val_loss: 3.4511 - val_mean_absolute_error: 1.4950
Epoch 561/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1806 - mean_absolute_error: 0.2636 - val_loss: 3.9072 - val_mean_absolute_error: 1.3773
Epoch 562/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1828 - mean_absolute_error: 0.2856 - val_loss: 3.3342 - val_mean_absolute_error: 1.4919
Epoch 563/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1806 - mean_absolute_error: 0.2729 - val_loss: 3.5048 - val_mean_absolute_error: 1.3009
Epoch 564/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1307 - mean_absolute_error: 0.2227 - val_loss: 3.3369 - val_mean_absolute_error: 1.4442
Epoch 565/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1307 - mean_absolute_error: 0.2246 - val_loss: 3.7179 - val_mean_absolute_error: 1.3087
Epoch 566/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1353 - mean_absolute_error: 0.2176 - val_loss: 3.2986 - val_mean_absolute_error: 1.4036
Epoch 567/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1588 - mean_absolute_error: 0.2072 - val_loss: 3.3621 - val_mean_absolute_error: 1.3303
Epoch 568/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5106 - mean_absolute_error: 0.3287 - val_loss: 3.6060 - val_mean_absolute_error: 1.4037
Epoch 569/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4405 - mean_absolute_error: 0.4029 - val_loss: 3.4911 - val_mean_absolute_error: 1.5200
Epoch 570/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2994 - mean_absolute_error: 0.3948 - val_loss: 3.1614 - val_mean_absolute_error: 1.3033
Epoch 571/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.2228 - mean_absolute_error: 0.3306 - val_loss: 3.5117 - val_mean_absolute_error: 1.3620
Epoch 572/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1848 - mean_absolute_error: 0.2934 - val_loss: 3.1472 - val_mean_absolute_error: 1.3044
Epoch 573/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1696 - mean_absolute_error: 0.2751 - val_loss: 3.3050 - val_mean_absolute_error: 1.3925
Epoch 574/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1403 - mean_absolute_error: 0.2552 - val_loss: 3.2587 - val_mean_absolute_error: 1.3527
Epoch 575/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1479 - mean_absolute_error: 0.2493 - val_loss: 3.3158 - val_mean_absolute_error: 1.3808
Epoch 576/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1921 - mean_absolute_error: 0.2597 - val_loss: 3.5943 - val_mean_absolute_error: 1.3792
Epoch 577/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1936 - mean_absolute_error: 0.2525 - val_loss: 3.3794 - val_mean_absolute_error: 1.4251
Epoch 578/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2339 - mean_absolute_error: 0.2694 - val_loss: 3.5526 - val_mean_absolute_error: 1.3307
Epoch 579/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1970 - mean_absolute_error: 0.2899 - val_loss: 3.5056 - val_mean_absolute_error: 1.4868
Epoch 580/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5033 - mean_absolute_error: 0.4149 - val_loss: 3.8747 - val_mean_absolute_error: 1.4704
Epoch 581/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5737 - mean_absolute_error: 0.5107 - val_loss: 3.9419 - val_mean_absolute_error: 1.6339
Epoch 582/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4885 - mean_absolute_error: 0.5077 - val_loss: 3.3599 - val_mean_absolute_error: 1.3219
Epoch 583/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3989 - mean_absolute_error: 0.4675 - val_loss: 3.2321 - val_mean_absolute_error: 1.4110
Epoch 584/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3980 - mean_absolute_error: 0.4474 - val_loss: 3.3459 - val_mean_absolute_error: 1.3410
Epoch 585/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3016 - mean_absolute_error: 0.3800 - val_loss: 3.4805 - val_mean_absolute_error: 1.4200
Epoch 586/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2393 - mean_absolute_error: 0.3482 - val_loss: 3.1327 - val_mean_absolute_error: 1.3392
Epoch 587/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2509 - mean_absolute_error: 0.3284 - val_loss: 3.2317 - val_mean_absolute_error: 1.4010
Epoch 588/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3550 - mean_absolute_error: 0.3684 - val_loss: 3.6554 - val_mean_absolute_error: 1.3597
Epoch 589/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3709 - mean_absolute_error: 0.3563 - val_loss: 3.4160 - val_mean_absolute_error: 1.4250
Epoch 590/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3285 - mean_absolute_error: 0.3660 - val_loss: 3.1268 - val_mean_absolute_error: 1.3763
Epoch 591/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2964 - mean_absolute_error: 0.3436 - val_loss: 3.6420 - val_mean_absolute_error: 1.4358
Epoch 592/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2612 - mean_absolute_error: 0.3552 - val_loss: 3.5723 - val_mean_absolute_error: 1.3237
Epoch 593/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1828 - mean_absolute_error: 0.2942 - val_loss: 3.4597 - val_mean_absolute_error: 1.4556
Epoch 594/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1698 - mean_absolute_error: 0.2738 - val_loss: 3.4346 - val_mean_absolute_error: 1.3811
Epoch 595/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1340 - mean_absolute_error: 0.2245 - val_loss: 3.5659 - val_mean_absolute_error: 1.4915
Epoch 596/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4244 - mean_absolute_error: 0.3664 - val_loss: 3.9644 - val_mean_absolute_error: 1.4077
Epoch 597/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3757 - mean_absolute_error: 0.3886 - val_loss: 3.4832 - val_mean_absolute_error: 1.5664
Epoch 598/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3949 - mean_absolute_error: 0.4636 - val_loss: 3.3320 - val_mean_absolute_error: 1.2037
Epoch 599/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3863 - mean_absolute_error: 0.4542 - val_loss: 3.9879 - val_mean_absolute_error: 1.4081
Epoch 600/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5023 - mean_absolute_error: 0.4993 - val_loss: 3.0238 - val_mean_absolute_error: 1.3780
Epoch 601/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5355 - mean_absolute_error: 0.4856 - val_loss: 3.0625 - val_mean_absolute_error: 1.3123
Epoch 602/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3496 - mean_absolute_error: 0.4230 - val_loss: 3.2361 - val_mean_absolute_error: 1.3708
Epoch 603/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4652 - mean_absolute_error: 0.4457 - val_loss: 4.4412 - val_mean_absolute_error: 1.5745
Epoch 604/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5374 - mean_absolute_error: 0.5194 - val_loss: 3.2979 - val_mean_absolute_error: 1.4116
Epoch 605/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4638 - mean_absolute_error: 0.4961 - val_loss: 3.5883 - val_mean_absolute_error: 1.4576
Epoch 606/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5845 - mean_absolute_error: 0.5025 - val_loss: 3.4923 - val_mean_absolute_error: 1.4220
Epoch 607/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5890 - mean_absolute_error: 0.5982 - val_loss: 2.8728 - val_mean_absolute_error: 1.3913
Epoch 608/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5732 - mean_absolute_error: 0.5923 - val_loss: 4.1742 - val_mean_absolute_error: 1.4598
Epoch 609/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4835 - mean_absolute_error: 0.5153 - val_loss: 2.6225 - val_mean_absolute_error: 1.2187
Epoch 610/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5169 - mean_absolute_error: 0.5521 - val_loss: 3.3965 - val_mean_absolute_error: 1.3185
Epoch 611/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4514 - mean_absolute_error: 0.4976 - val_loss: 3.7197 - val_mean_absolute_error: 1.5295
Epoch 612/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4388 - mean_absolute_error: 0.4900 - val_loss: 3.2193 - val_mean_absolute_error: 1.3680
Epoch 613/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3970 - mean_absolute_error: 0.4768 - val_loss: 3.7503 - val_mean_absolute_error: 1.4776
Epoch 614/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3346 - mean_absolute_error: 0.4214 - val_loss: 3.0086 - val_mean_absolute_error: 1.2805
Epoch 615/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2567 - mean_absolute_error: 0.3484 - val_loss: 3.0572 - val_mean_absolute_error: 1.3429
Epoch 616/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1742 - mean_absolute_error: 0.2823 - val_loss: 3.4551 - val_mean_absolute_error: 1.3490
Epoch 617/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1222 - mean_absolute_error: 0.2262 - val_loss: 3.4274 - val_mean_absolute_error: 1.4016
Epoch 618/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1444 - mean_absolute_error: 0.1995 - val_loss: 3.3644 - val_mean_absolute_error: 1.3477
Epoch 619/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1268 - mean_absolute_error: 0.1921 - val_loss: 3.3262 - val_mean_absolute_error: 1.4142
Epoch 620/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1010 - mean_absolute_error: 0.1978 - val_loss: 3.3231 - val_mean_absolute_error: 1.3524
Epoch 621/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0907 - mean_absolute_error: 0.1660 - val_loss: 3.2394 - val_mean_absolute_error: 1.3439
Epoch 622/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0911 - mean_absolute_error: 0.1692 - val_loss: 3.4426 - val_mean_absolute_error: 1.3577
Epoch 623/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.1354 - mean_absolute_error: 0.2006 - val_loss: 3.1838 - val_mean_absolute_error: 1.3658
Epoch 624/1000
7/7 [==============================] - 0s 37ms/step - loss: 0.1283 - mean_absolute_error: 0.2251 - val_loss: 3.5653 - val_mean_absolute_error: 1.3488
Epoch 625/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.1107 - mean_absolute_error: 0.2193 - val_loss: 3.3237 - val_mean_absolute_error: 1.3895
Epoch 626/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1415 - mean_absolute_error: 0.2326 - val_loss: 3.2274 - val_mean_absolute_error: 1.3648
Epoch 627/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1074 - mean_absolute_error: 0.1998 - val_loss: 3.3602 - val_mean_absolute_error: 1.3690
Epoch 628/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1028 - mean_absolute_error: 0.1627 - val_loss: 3.3060 - val_mean_absolute_error: 1.3677
Epoch 629/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1184 - mean_absolute_error: 0.1752 - val_loss: 3.2306 - val_mean_absolute_error: 1.3607
Epoch 630/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0981 - mean_absolute_error: 0.1681 - val_loss: 3.2720 - val_mean_absolute_error: 1.3091
Epoch 631/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0869 - mean_absolute_error: 0.1670 - val_loss: 3.4016 - val_mean_absolute_error: 1.3863
Epoch 632/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1850 - mean_absolute_error: 0.2047 - val_loss: 3.3266 - val_mean_absolute_error: 1.3645
Epoch 633/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1345 - mean_absolute_error: 0.1703 - val_loss: 3.4918 - val_mean_absolute_error: 1.4070
Epoch 634/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1280 - mean_absolute_error: 0.2089 - val_loss: 3.2649 - val_mean_absolute_error: 1.3232
Epoch 635/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1185 - mean_absolute_error: 0.2086 - val_loss: 3.4599 - val_mean_absolute_error: 1.3534
Epoch 636/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.0859 - mean_absolute_error: 0.2120 - val_loss: 3.4855 - val_mean_absolute_error: 1.3249
Epoch 637/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1530 - mean_absolute_error: 0.2146 - val_loss: 3.2503 - val_mean_absolute_error: 1.3893
Epoch 638/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1356 - mean_absolute_error: 0.2488 - val_loss: 3.6138 - val_mean_absolute_error: 1.4166
Epoch 639/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1558 - mean_absolute_error: 0.2253 - val_loss: 3.7453 - val_mean_absolute_error: 1.3581
Epoch 640/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2032 - mean_absolute_error: 0.2542 - val_loss: 3.3424 - val_mean_absolute_error: 1.4697
Epoch 641/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8019 - mean_absolute_error: 0.4995 - val_loss: 4.1303 - val_mean_absolute_error: 1.5337
Epoch 642/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6292 - mean_absolute_error: 0.4473 - val_loss: 3.8727 - val_mean_absolute_error: 1.6337
Epoch 643/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7157 - mean_absolute_error: 0.5344 - val_loss: 3.3982 - val_mean_absolute_error: 1.4301
Epoch 644/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3756 - mean_absolute_error: 0.4274 - val_loss: 3.2630 - val_mean_absolute_error: 1.3590
Epoch 645/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4955 - mean_absolute_error: 0.4320 - val_loss: 3.8629 - val_mean_absolute_error: 1.3556
Epoch 646/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4902 - mean_absolute_error: 0.4505 - val_loss: 3.6552 - val_mean_absolute_error: 1.5765
Epoch 647/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3718 - mean_absolute_error: 0.4372 - val_loss: 3.6509 - val_mean_absolute_error: 1.4045
Epoch 648/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3507 - mean_absolute_error: 0.4066 - val_loss: 3.7606 - val_mean_absolute_error: 1.5469
Epoch 649/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2186 - mean_absolute_error: 0.3384 - val_loss: 3.3785 - val_mean_absolute_error: 1.3792
Epoch 650/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1944 - mean_absolute_error: 0.3062 - val_loss: 3.2753 - val_mean_absolute_error: 1.4544
Epoch 651/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1424 - mean_absolute_error: 0.2632 - val_loss: 3.5414 - val_mean_absolute_error: 1.3947
Epoch 652/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1202 - mean_absolute_error: 0.2270 - val_loss: 3.3666 - val_mean_absolute_error: 1.4152
Epoch 653/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0921 - mean_absolute_error: 0.1651 - val_loss: 3.4395 - val_mean_absolute_error: 1.3685
Epoch 654/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0814 - mean_absolute_error: 0.1467 - val_loss: 3.3231 - val_mean_absolute_error: 1.4288
Epoch 655/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0805 - mean_absolute_error: 0.1485 - val_loss: 3.3958 - val_mean_absolute_error: 1.3964
Epoch 656/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0941 - mean_absolute_error: 0.1387 - val_loss: 3.4481 - val_mean_absolute_error: 1.3934
Epoch 657/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0575 - mean_absolute_error: 0.1240 - val_loss: 3.5106 - val_mean_absolute_error: 1.4130
Epoch 658/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1049 - mean_absolute_error: 0.1463 - val_loss: 3.3500 - val_mean_absolute_error: 1.4291
Epoch 659/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2933 - mean_absolute_error: 0.3241 - val_loss: 3.7543 - val_mean_absolute_error: 1.4166
Epoch 660/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4827 - mean_absolute_error: 0.3995 - val_loss: 3.6131 - val_mean_absolute_error: 1.5173
Epoch 661/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4172 - mean_absolute_error: 0.4149 - val_loss: 3.1888 - val_mean_absolute_error: 1.4244
Epoch 662/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2691 - mean_absolute_error: 0.3531 - val_loss: 3.4749 - val_mean_absolute_error: 1.3180
Epoch 663/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2495 - mean_absolute_error: 0.3506 - val_loss: 3.1539 - val_mean_absolute_error: 1.3428
Epoch 664/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2029 - mean_absolute_error: 0.2977 - val_loss: 3.4995 - val_mean_absolute_error: 1.4132
Epoch 665/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1833 - mean_absolute_error: 0.2959 - val_loss: 3.6055 - val_mean_absolute_error: 1.4312
Epoch 666/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1661 - mean_absolute_error: 0.2636 - val_loss: 3.3535 - val_mean_absolute_error: 1.3792
Epoch 667/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1442 - mean_absolute_error: 0.2250 - val_loss: 3.2175 - val_mean_absolute_error: 1.3780
Epoch 668/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0985 - mean_absolute_error: 0.1998 - val_loss: 3.1494 - val_mean_absolute_error: 1.3178
Epoch 669/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1141 - mean_absolute_error: 0.2001 - val_loss: 3.4019 - val_mean_absolute_error: 1.4340
Epoch 670/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.1004 - mean_absolute_error: 0.1822 - val_loss: 3.4945 - val_mean_absolute_error: 1.3559
Epoch 671/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0876 - mean_absolute_error: 0.1850 - val_loss: 3.3864 - val_mean_absolute_error: 1.3901
Epoch 672/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1204 - mean_absolute_error: 0.1929 - val_loss: 3.4271 - val_mean_absolute_error: 1.3620
Epoch 673/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1078 - mean_absolute_error: 0.1996 - val_loss: 3.1479 - val_mean_absolute_error: 1.3659
Epoch 674/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2380 - mean_absolute_error: 0.2447 - val_loss: 3.6526 - val_mean_absolute_error: 1.4147
Epoch 675/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1633 - mean_absolute_error: 0.2814 - val_loss: 3.3327 - val_mean_absolute_error: 1.3704
Epoch 676/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1328 - mean_absolute_error: 0.2357 - val_loss: 3.7247 - val_mean_absolute_error: 1.4248
Epoch 677/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.1805 - mean_absolute_error: 0.2566 - val_loss: 3.3603 - val_mean_absolute_error: 1.4188
Epoch 678/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1743 - mean_absolute_error: 0.2370 - val_loss: 3.3908 - val_mean_absolute_error: 1.3551
Epoch 679/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1966 - mean_absolute_error: 0.2565 - val_loss: 3.3000 - val_mean_absolute_error: 1.4437
Epoch 680/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1176 - mean_absolute_error: 0.2358 - val_loss: 3.7472 - val_mean_absolute_error: 1.4600
Epoch 681/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1147 - mean_absolute_error: 0.2242 - val_loss: 3.4427 - val_mean_absolute_error: 1.3996
Epoch 682/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1027 - mean_absolute_error: 0.2037 - val_loss: 3.2489 - val_mean_absolute_error: 1.3785
Epoch 683/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1522 - mean_absolute_error: 0.2248 - val_loss: 3.6368 - val_mean_absolute_error: 1.4051
Epoch 684/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1251 - mean_absolute_error: 0.2392 - val_loss: 2.9815 - val_mean_absolute_error: 1.3332
Epoch 685/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.2824 - mean_absolute_error: 0.3065 - val_loss: 3.7133 - val_mean_absolute_error: 1.4190
Epoch 686/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1752 - mean_absolute_error: 0.2746 - val_loss: 3.2354 - val_mean_absolute_error: 1.4103
Epoch 687/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2043 - mean_absolute_error: 0.3021 - val_loss: 3.4390 - val_mean_absolute_error: 1.3958
Epoch 688/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1647 - mean_absolute_error: 0.2710 - val_loss: 3.0355 - val_mean_absolute_error: 1.3219
Epoch 689/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2287 - mean_absolute_error: 0.3144 - val_loss: 3.0986 - val_mean_absolute_error: 1.4079
Epoch 690/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1360 - mean_absolute_error: 0.2577 - val_loss: 3.5288 - val_mean_absolute_error: 1.3817
Epoch 691/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1131 - mean_absolute_error: 0.2256 - val_loss: 3.3555 - val_mean_absolute_error: 1.4345
Epoch 692/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1005 - mean_absolute_error: 0.2257 - val_loss: 3.4560 - val_mean_absolute_error: 1.4049
Epoch 693/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0940 - mean_absolute_error: 0.1968 - val_loss: 3.2374 - val_mean_absolute_error: 1.4369
Epoch 694/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.0978 - mean_absolute_error: 0.1777 - val_loss: 3.3431 - val_mean_absolute_error: 1.3511
Epoch 695/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1065 - mean_absolute_error: 0.1746 - val_loss: 3.3402 - val_mean_absolute_error: 1.4332
Epoch 696/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.0823 - mean_absolute_error: 0.1546 - val_loss: 3.4828 - val_mean_absolute_error: 1.3344
Epoch 697/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.0672 - mean_absolute_error: 0.1456 - val_loss: 3.3973 - val_mean_absolute_error: 1.4462
Epoch 698/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0976 - mean_absolute_error: 0.1509 - val_loss: 3.3396 - val_mean_absolute_error: 1.3839
Epoch 699/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0937 - mean_absolute_error: 0.1659 - val_loss: 3.4587 - val_mean_absolute_error: 1.4493
Epoch 700/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.1123 - mean_absolute_error: 0.1873 - val_loss: 3.4025 - val_mean_absolute_error: 1.3526
Epoch 701/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.0733 - mean_absolute_error: 0.1684 - val_loss: 3.3406 - val_mean_absolute_error: 1.4507
Epoch 702/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0853 - mean_absolute_error: 0.1714 - val_loss: 3.4107 - val_mean_absolute_error: 1.3604
Epoch 703/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0718 - mean_absolute_error: 0.1647 - val_loss: 3.5001 - val_mean_absolute_error: 1.4366
Epoch 704/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0578 - mean_absolute_error: 0.1457 - val_loss: 3.4143 - val_mean_absolute_error: 1.3706
Epoch 705/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0573 - mean_absolute_error: 0.1303 - val_loss: 3.2763 - val_mean_absolute_error: 1.4206
Epoch 706/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0876 - mean_absolute_error: 0.1549 - val_loss: 3.5021 - val_mean_absolute_error: 1.3993
Epoch 707/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0495 - mean_absolute_error: 0.1378 - val_loss: 3.4076 - val_mean_absolute_error: 1.4314
Epoch 708/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0784 - mean_absolute_error: 0.1576 - val_loss: 3.3441 - val_mean_absolute_error: 1.3920
Epoch 709/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0616 - mean_absolute_error: 0.1412 - val_loss: 3.3888 - val_mean_absolute_error: 1.4372
Epoch 710/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0503 - mean_absolute_error: 0.1302 - val_loss: 3.3840 - val_mean_absolute_error: 1.3726
Epoch 711/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0932 - mean_absolute_error: 0.1634 - val_loss: 3.4313 - val_mean_absolute_error: 1.4149
Epoch 712/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1875 - mean_absolute_error: 0.2699 - val_loss: 3.5368 - val_mean_absolute_error: 1.4340
Epoch 713/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3421 - mean_absolute_error: 0.3091 - val_loss: 3.7654 - val_mean_absolute_error: 1.5612
Epoch 714/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2826 - mean_absolute_error: 0.3114 - val_loss: 3.4875 - val_mean_absolute_error: 1.3900
Epoch 715/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3337 - mean_absolute_error: 0.3745 - val_loss: 3.2865 - val_mean_absolute_error: 1.4344
Epoch 716/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2577 - mean_absolute_error: 0.3666 - val_loss: 3.5195 - val_mean_absolute_error: 1.2825
Epoch 717/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2307 - mean_absolute_error: 0.3535 - val_loss: 3.2804 - val_mean_absolute_error: 1.4325
Epoch 718/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1914 - mean_absolute_error: 0.3246 - val_loss: 3.5666 - val_mean_absolute_error: 1.4267
Epoch 719/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1757 - mean_absolute_error: 0.2979 - val_loss: 3.4307 - val_mean_absolute_error: 1.4308
Epoch 720/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1758 - mean_absolute_error: 0.2959 - val_loss: 3.1991 - val_mean_absolute_error: 1.3823
Epoch 721/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1367 - mean_absolute_error: 0.2498 - val_loss: 3.2550 - val_mean_absolute_error: 1.3721
Epoch 722/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1314 - mean_absolute_error: 0.2406 - val_loss: 3.0511 - val_mean_absolute_error: 1.3002
Epoch 723/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2237 - mean_absolute_error: 0.2570 - val_loss: 3.2851 - val_mean_absolute_error: 1.3837
Epoch 724/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1055 - mean_absolute_error: 0.2540 - val_loss: 3.3565 - val_mean_absolute_error: 1.4099
Epoch 725/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1132 - mean_absolute_error: 0.2189 - val_loss: 3.2252 - val_mean_absolute_error: 1.3280
Epoch 726/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1220 - mean_absolute_error: 0.2085 - val_loss: 3.2110 - val_mean_absolute_error: 1.3327
Epoch 727/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.0735 - mean_absolute_error: 0.1763 - val_loss: 3.2814 - val_mean_absolute_error: 1.3609
Epoch 728/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0669 - mean_absolute_error: 0.1604 - val_loss: 3.4834 - val_mean_absolute_error: 1.4147
Epoch 729/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0878 - mean_absolute_error: 0.1850 - val_loss: 3.3066 - val_mean_absolute_error: 1.3186
Epoch 730/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0732 - mean_absolute_error: 0.1633 - val_loss: 3.4093 - val_mean_absolute_error: 1.4168
Epoch 731/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0610 - mean_absolute_error: 0.1511 - val_loss: 3.2538 - val_mean_absolute_error: 1.3557
Epoch 732/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0442 - mean_absolute_error: 0.1373 - val_loss: 3.1860 - val_mean_absolute_error: 1.3742
Epoch 733/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0639 - mean_absolute_error: 0.1364 - val_loss: 3.4212 - val_mean_absolute_error: 1.3410
Epoch 734/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1126 - mean_absolute_error: 0.1560 - val_loss: 3.3468 - val_mean_absolute_error: 1.4075
Epoch 735/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0605 - mean_absolute_error: 0.1579 - val_loss: 3.2782 - val_mean_absolute_error: 1.3739
Epoch 736/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1051 - mean_absolute_error: 0.1823 - val_loss: 3.6057 - val_mean_absolute_error: 1.4162
Epoch 737/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0994 - mean_absolute_error: 0.1845 - val_loss: 3.3593 - val_mean_absolute_error: 1.4306
Epoch 738/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0657 - mean_absolute_error: 0.1678 - val_loss: 3.5414 - val_mean_absolute_error: 1.3767
Epoch 739/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1115 - mean_absolute_error: 0.1938 - val_loss: 3.4122 - val_mean_absolute_error: 1.4419
Epoch 740/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1107 - mean_absolute_error: 0.1960 - val_loss: 3.4048 - val_mean_absolute_error: 1.3392
Epoch 741/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0675 - mean_absolute_error: 0.1872 - val_loss: 3.3296 - val_mean_absolute_error: 1.4342
Epoch 742/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0932 - mean_absolute_error: 0.1775 - val_loss: 3.3693 - val_mean_absolute_error: 1.3249
Epoch 743/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0788 - mean_absolute_error: 0.1905 - val_loss: 3.4556 - val_mean_absolute_error: 1.5205
Epoch 744/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0981 - mean_absolute_error: 0.2164 - val_loss: 3.4908 - val_mean_absolute_error: 1.3029
Epoch 745/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1089 - mean_absolute_error: 0.2071 - val_loss: 3.2958 - val_mean_absolute_error: 1.3750
Epoch 746/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1226 - mean_absolute_error: 0.2049 - val_loss: 3.1207 - val_mean_absolute_error: 1.3412
Epoch 747/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1025 - mean_absolute_error: 0.2198 - val_loss: 3.2767 - val_mean_absolute_error: 1.3850
Epoch 748/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1052 - mean_absolute_error: 0.1897 - val_loss: 3.5115 - val_mean_absolute_error: 1.4520
Epoch 749/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1643 - mean_absolute_error: 0.2237 - val_loss: 3.2442 - val_mean_absolute_error: 1.3369
Epoch 750/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2668 - mean_absolute_error: 0.2603 - val_loss: 3.5772 - val_mean_absolute_error: 1.4497
Epoch 751/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1318 - mean_absolute_error: 0.2501 - val_loss: 3.3588 - val_mean_absolute_error: 1.4254
Epoch 752/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1138 - mean_absolute_error: 0.2384 - val_loss: 3.3676 - val_mean_absolute_error: 1.3584
Epoch 753/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1358 - mean_absolute_error: 0.2736 - val_loss: 3.5573 - val_mean_absolute_error: 1.4374
Epoch 754/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1577 - mean_absolute_error: 0.2816 - val_loss: 3.4275 - val_mean_absolute_error: 1.3330
Epoch 755/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1538 - mean_absolute_error: 0.2546 - val_loss: 3.4071 - val_mean_absolute_error: 1.4092
Epoch 756/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2877 - mean_absolute_error: 0.3684 - val_loss: 3.2809 - val_mean_absolute_error: 1.3057
Epoch 757/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2560 - mean_absolute_error: 0.3737 - val_loss: 3.2648 - val_mean_absolute_error: 1.4174
Epoch 758/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.2928 - mean_absolute_error: 0.3583 - val_loss: 3.6294 - val_mean_absolute_error: 1.4615
Epoch 759/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3079 - mean_absolute_error: 0.4112 - val_loss: 3.3535 - val_mean_absolute_error: 1.3994
Epoch 760/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1663 - mean_absolute_error: 0.2889 - val_loss: 3.4975 - val_mean_absolute_error: 1.4045
Epoch 761/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.1832 - mean_absolute_error: 0.2958 - val_loss: 3.1774 - val_mean_absolute_error: 1.3989
Epoch 762/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1932 - mean_absolute_error: 0.2997 - val_loss: 3.4863 - val_mean_absolute_error: 1.3648
Epoch 763/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2434 - mean_absolute_error: 0.3414 - val_loss: 3.3872 - val_mean_absolute_error: 1.4505
Epoch 764/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3295 - mean_absolute_error: 0.3599 - val_loss: 3.4941 - val_mean_absolute_error: 1.3308
Epoch 765/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.6346 - mean_absolute_error: 0.4390 - val_loss: 3.9518 - val_mean_absolute_error: 1.6119
Epoch 766/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.9051 - mean_absolute_error: 0.5061 - val_loss: 3.7646 - val_mean_absolute_error: 1.4175
Epoch 767/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4286 - mean_absolute_error: 0.4692 - val_loss: 3.6122 - val_mean_absolute_error: 1.5754
Epoch 768/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5159 - mean_absolute_error: 0.5390 - val_loss: 3.5115 - val_mean_absolute_error: 1.2957
Epoch 769/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3597 - mean_absolute_error: 0.4058 - val_loss: 3.7962 - val_mean_absolute_error: 1.5562
Epoch 770/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5717 - mean_absolute_error: 0.4471 - val_loss: 3.6124 - val_mean_absolute_error: 1.3861
Epoch 771/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3569 - mean_absolute_error: 0.4327 - val_loss: 3.9025 - val_mean_absolute_error: 1.5233
Epoch 772/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2681 - mean_absolute_error: 0.3571 - val_loss: 3.3930 - val_mean_absolute_error: 1.3833
Epoch 773/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2508 - mean_absolute_error: 0.3922 - val_loss: 3.4541 - val_mean_absolute_error: 1.4986
Epoch 774/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2799 - mean_absolute_error: 0.3566 - val_loss: 3.8323 - val_mean_absolute_error: 1.4579
Epoch 775/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2423 - mean_absolute_error: 0.3825 - val_loss: 3.4487 - val_mean_absolute_error: 1.4297
Epoch 776/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.2157 - mean_absolute_error: 0.3420 - val_loss: 2.9573 - val_mean_absolute_error: 1.3247
Epoch 777/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1768 - mean_absolute_error: 0.3014 - val_loss: 3.6455 - val_mean_absolute_error: 1.4153
Epoch 778/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2062 - mean_absolute_error: 0.3212 - val_loss: 3.1450 - val_mean_absolute_error: 1.3165
Epoch 779/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1773 - mean_absolute_error: 0.3265 - val_loss: 3.3665 - val_mean_absolute_error: 1.4497
Epoch 780/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1733 - mean_absolute_error: 0.3083 - val_loss: 3.6120 - val_mean_absolute_error: 1.3699
Epoch 781/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2052 - mean_absolute_error: 0.3128 - val_loss: 3.5079 - val_mean_absolute_error: 1.5051
Epoch 782/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3169 - mean_absolute_error: 0.3418 - val_loss: 3.4786 - val_mean_absolute_error: 1.3783
Epoch 783/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3115 - mean_absolute_error: 0.3986 - val_loss: 3.8929 - val_mean_absolute_error: 1.6440
Epoch 784/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2955 - mean_absolute_error: 0.4128 - val_loss: 3.5344 - val_mean_absolute_error: 1.3339
Epoch 785/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2457 - mean_absolute_error: 0.3506 - val_loss: 3.1875 - val_mean_absolute_error: 1.5070
Epoch 786/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2031 - mean_absolute_error: 0.3123 - val_loss: 3.4421 - val_mean_absolute_error: 1.3658
Epoch 787/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1589 - mean_absolute_error: 0.2945 - val_loss: 3.5331 - val_mean_absolute_error: 1.4927
Epoch 788/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1338 - mean_absolute_error: 0.2630 - val_loss: 3.0752 - val_mean_absolute_error: 1.3329
Epoch 789/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1383 - mean_absolute_error: 0.2823 - val_loss: 3.2069 - val_mean_absolute_error: 1.3919
Epoch 790/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1416 - mean_absolute_error: 0.2366 - val_loss: 3.3179 - val_mean_absolute_error: 1.3719
Epoch 791/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2394 - mean_absolute_error: 0.3229 - val_loss: 3.4385 - val_mean_absolute_error: 1.4907
Epoch 792/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5823 - mean_absolute_error: 0.4084 - val_loss: 3.6397 - val_mean_absolute_error: 1.4616
Epoch 793/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5346 - mean_absolute_error: 0.3935 - val_loss: 3.7231 - val_mean_absolute_error: 1.6046
Epoch 794/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3377 - mean_absolute_error: 0.3449 - val_loss: 3.3338 - val_mean_absolute_error: 1.3554
Epoch 795/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3069 - mean_absolute_error: 0.3318 - val_loss: 3.5278 - val_mean_absolute_error: 1.4455
Epoch 796/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2804 - mean_absolute_error: 0.3474 - val_loss: 2.9664 - val_mean_absolute_error: 1.2770
Epoch 797/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2774 - mean_absolute_error: 0.3255 - val_loss: 3.1331 - val_mean_absolute_error: 1.3340
Epoch 798/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2214 - mean_absolute_error: 0.3365 - val_loss: 3.4855 - val_mean_absolute_error: 1.4662
Epoch 799/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2235 - mean_absolute_error: 0.3379 - val_loss: 3.1577 - val_mean_absolute_error: 1.3893
Epoch 800/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1726 - mean_absolute_error: 0.2933 - val_loss: 3.2809 - val_mean_absolute_error: 1.3906
Epoch 801/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1427 - mean_absolute_error: 0.2631 - val_loss: 3.3366 - val_mean_absolute_error: 1.4205
Epoch 802/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1816 - mean_absolute_error: 0.2966 - val_loss: 3.3844 - val_mean_absolute_error: 1.3808
Epoch 803/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1458 - mean_absolute_error: 0.2790 - val_loss: 2.9640 - val_mean_absolute_error: 1.4175
Epoch 804/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1598 - mean_absolute_error: 0.2924 - val_loss: 3.3643 - val_mean_absolute_error: 1.3578
Epoch 805/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1262 - mean_absolute_error: 0.2717 - val_loss: 3.5099 - val_mean_absolute_error: 1.4924
Epoch 806/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1283 - mean_absolute_error: 0.2770 - val_loss: 3.2034 - val_mean_absolute_error: 1.3444
Epoch 807/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1084 - mean_absolute_error: 0.2504 - val_loss: 3.6722 - val_mean_absolute_error: 1.4554
Epoch 808/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1351 - mean_absolute_error: 0.2587 - val_loss: 3.3197 - val_mean_absolute_error: 1.3852
Epoch 809/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1303 - mean_absolute_error: 0.2371 - val_loss: 3.2059 - val_mean_absolute_error: 1.3995
Epoch 810/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0937 - mean_absolute_error: 0.1851 - val_loss: 3.3015 - val_mean_absolute_error: 1.4080
Epoch 811/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0622 - mean_absolute_error: 0.1533 - val_loss: 3.2923 - val_mean_absolute_error: 1.3802
Epoch 812/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0527 - mean_absolute_error: 0.1442 - val_loss: 3.2640 - val_mean_absolute_error: 1.3983
Epoch 813/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0466 - mean_absolute_error: 0.1192 - val_loss: 3.3644 - val_mean_absolute_error: 1.4070
Epoch 814/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3200 - mean_absolute_error: 0.2358 - val_loss: 3.8180 - val_mean_absolute_error: 1.4956
Epoch 815/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3255 - mean_absolute_error: 0.2866 - val_loss: 3.3871 - val_mean_absolute_error: 1.4879
Epoch 816/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2583 - mean_absolute_error: 0.2676 - val_loss: 3.4413 - val_mean_absolute_error: 1.3879
Epoch 817/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1862 - mean_absolute_error: 0.2531 - val_loss: 3.4430 - val_mean_absolute_error: 1.3481
Epoch 818/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.1404 - mean_absolute_error: 0.2285 - val_loss: 3.2876 - val_mean_absolute_error: 1.3777
Epoch 819/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1150 - mean_absolute_error: 0.1934 - val_loss: 3.2798 - val_mean_absolute_error: 1.3675
Epoch 820/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1714 - mean_absolute_error: 0.1936 - val_loss: 3.2912 - val_mean_absolute_error: 1.4404
Epoch 821/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0865 - mean_absolute_error: 0.1973 - val_loss: 3.4526 - val_mean_absolute_error: 1.4011
Epoch 822/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.0863 - mean_absolute_error: 0.1760 - val_loss: 3.2978 - val_mean_absolute_error: 1.4423
Epoch 823/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.0607 - mean_absolute_error: 0.1539 - val_loss: 3.4005 - val_mean_absolute_error: 1.3729
Epoch 824/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0524 - mean_absolute_error: 0.1371 - val_loss: 3.3587 - val_mean_absolute_error: 1.4309
Epoch 825/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0722 - mean_absolute_error: 0.1423 - val_loss: 3.3119 - val_mean_absolute_error: 1.3702
Epoch 826/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1064 - mean_absolute_error: 0.1640 - val_loss: 3.4106 - val_mean_absolute_error: 1.4463
Epoch 827/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0835 - mean_absolute_error: 0.2100 - val_loss: 3.4616 - val_mean_absolute_error: 1.3800
Epoch 828/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1720 - mean_absolute_error: 0.2173 - val_loss: 3.3714 - val_mean_absolute_error: 1.4410
Epoch 829/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1722 - mean_absolute_error: 0.2172 - val_loss: 3.2239 - val_mean_absolute_error: 1.4161
Epoch 830/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1586 - mean_absolute_error: 0.2447 - val_loss: 3.2497 - val_mean_absolute_error: 1.3788
Epoch 831/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.1069 - mean_absolute_error: 0.2381 - val_loss: 3.4700 - val_mean_absolute_error: 1.4454
Epoch 832/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1147 - mean_absolute_error: 0.2445 - val_loss: 3.3436 - val_mean_absolute_error: 1.3182
Epoch 833/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1159 - mean_absolute_error: 0.2443 - val_loss: 3.1919 - val_mean_absolute_error: 1.4735
Epoch 834/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1376 - mean_absolute_error: 0.2411 - val_loss: 3.4327 - val_mean_absolute_error: 1.3324
Epoch 835/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1575 - mean_absolute_error: 0.2747 - val_loss: 3.4066 - val_mean_absolute_error: 1.4506
Epoch 836/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1316 - mean_absolute_error: 0.2826 - val_loss: 3.1624 - val_mean_absolute_error: 1.2880
Epoch 837/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1281 - mean_absolute_error: 0.2586 - val_loss: 3.3713 - val_mean_absolute_error: 1.4195
Epoch 838/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0702 - mean_absolute_error: 0.2030 - val_loss: 3.3721 - val_mean_absolute_error: 1.3531
Epoch 839/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0990 - mean_absolute_error: 0.1802 - val_loss: 3.1932 - val_mean_absolute_error: 1.4253
Epoch 840/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0744 - mean_absolute_error: 0.1712 - val_loss: 3.4039 - val_mean_absolute_error: 1.4152
Epoch 841/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.0693 - mean_absolute_error: 0.1759 - val_loss: 3.2726 - val_mean_absolute_error: 1.3255
Epoch 842/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0784 - mean_absolute_error: 0.1931 - val_loss: 3.2846 - val_mean_absolute_error: 1.3917
Epoch 843/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0936 - mean_absolute_error: 0.2092 - val_loss: 3.1582 - val_mean_absolute_error: 1.3359
Epoch 844/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1023 - mean_absolute_error: 0.1966 - val_loss: 3.3507 - val_mean_absolute_error: 1.4557
Epoch 845/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1344 - mean_absolute_error: 0.2032 - val_loss: 3.1959 - val_mean_absolute_error: 1.3719
Epoch 846/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1179 - mean_absolute_error: 0.2264 - val_loss: 3.3773 - val_mean_absolute_error: 1.3686
Epoch 847/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1547 - mean_absolute_error: 0.2604 - val_loss: 3.4130 - val_mean_absolute_error: 1.4285
Epoch 848/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1807 - mean_absolute_error: 0.2908 - val_loss: 3.5585 - val_mean_absolute_error: 1.3976
Epoch 849/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7540 - mean_absolute_error: 0.5584 - val_loss: 3.8985 - val_mean_absolute_error: 1.5715
Epoch 850/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6416 - mean_absolute_error: 0.5538 - val_loss: 2.8567 - val_mean_absolute_error: 1.2853
Epoch 851/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6155 - mean_absolute_error: 0.6180 - val_loss: 3.2027 - val_mean_absolute_error: 1.4052
Epoch 852/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4945 - mean_absolute_error: 0.5053 - val_loss: 3.6788 - val_mean_absolute_error: 1.4251
Epoch 853/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9051 - mean_absolute_error: 0.6646 - val_loss: 3.3608 - val_mean_absolute_error: 1.4899
Epoch 854/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7677 - mean_absolute_error: 0.6141 - val_loss: 4.2233 - val_mean_absolute_error: 1.4472
Epoch 855/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5869 - mean_absolute_error: 0.5962 - val_loss: 3.1306 - val_mean_absolute_error: 1.3321
Epoch 856/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5523 - mean_absolute_error: 0.5612 - val_loss: 3.4050 - val_mean_absolute_error: 1.4905
Epoch 857/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.6388 - mean_absolute_error: 0.6218 - val_loss: 3.1652 - val_mean_absolute_error: 1.3330
Epoch 858/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5587 - mean_absolute_error: 0.5778 - val_loss: 3.3888 - val_mean_absolute_error: 1.3603
Epoch 859/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3322 - mean_absolute_error: 0.4446 - val_loss: 3.0320 - val_mean_absolute_error: 1.3798
Epoch 860/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3354 - mean_absolute_error: 0.4266 - val_loss: 3.7448 - val_mean_absolute_error: 1.4572
Epoch 861/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2302 - mean_absolute_error: 0.3698 - val_loss: 3.1911 - val_mean_absolute_error: 1.3418
Epoch 862/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2791 - mean_absolute_error: 0.3815 - val_loss: 3.6040 - val_mean_absolute_error: 1.4545
Epoch 863/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2402 - mean_absolute_error: 0.3772 - val_loss: 3.3521 - val_mean_absolute_error: 1.3213
Epoch 864/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1308 - mean_absolute_error: 0.2853 - val_loss: 3.1655 - val_mean_absolute_error: 1.3699
Epoch 865/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1929 - mean_absolute_error: 0.3116 - val_loss: 3.6820 - val_mean_absolute_error: 1.4110
Epoch 866/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1678 - mean_absolute_error: 0.3025 - val_loss: 3.0550 - val_mean_absolute_error: 1.4416
Epoch 867/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1072 - mean_absolute_error: 0.2578 - val_loss: 3.4922 - val_mean_absolute_error: 1.3768
Epoch 868/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1120 - mean_absolute_error: 0.2495 - val_loss: 3.0948 - val_mean_absolute_error: 1.4457
Epoch 869/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.0738 - mean_absolute_error: 0.1989 - val_loss: 3.4722 - val_mean_absolute_error: 1.3691
Epoch 870/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0898 - mean_absolute_error: 0.2131 - val_loss: 3.3030 - val_mean_absolute_error: 1.4533
Epoch 871/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0924 - mean_absolute_error: 0.2207 - val_loss: 3.5300 - val_mean_absolute_error: 1.3843
Epoch 872/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1152 - mean_absolute_error: 0.2387 - val_loss: 3.4986 - val_mean_absolute_error: 1.4419
Epoch 873/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1107 - mean_absolute_error: 0.2295 - val_loss: 3.2835 - val_mean_absolute_error: 1.3727
Epoch 874/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1197 - mean_absolute_error: 0.2324 - val_loss: 3.3058 - val_mean_absolute_error: 1.4070
Epoch 875/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.0833 - mean_absolute_error: 0.1986 - val_loss: 3.4095 - val_mean_absolute_error: 1.4294
Epoch 876/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1744 - mean_absolute_error: 0.2395 - val_loss: 3.4604 - val_mean_absolute_error: 1.3862
Epoch 877/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1071 - mean_absolute_error: 0.2499 - val_loss: 3.4416 - val_mean_absolute_error: 1.4396
Epoch 878/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0948 - mean_absolute_error: 0.2202 - val_loss: 3.4440 - val_mean_absolute_error: 1.4156
Epoch 879/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0852 - mean_absolute_error: 0.2287 - val_loss: 3.2672 - val_mean_absolute_error: 1.3833
Epoch 880/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0877 - mean_absolute_error: 0.2152 - val_loss: 3.5455 - val_mean_absolute_error: 1.4405
Epoch 881/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.0828 - mean_absolute_error: 0.2044 - val_loss: 3.3163 - val_mean_absolute_error: 1.4045
Epoch 882/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.0980 - mean_absolute_error: 0.2220 - val_loss: 3.4795 - val_mean_absolute_error: 1.4241
Epoch 883/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0903 - mean_absolute_error: 0.2049 - val_loss: 3.2267 - val_mean_absolute_error: 1.3808
Epoch 884/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0586 - mean_absolute_error: 0.1782 - val_loss: 3.2076 - val_mean_absolute_error: 1.3312
Epoch 885/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3780 - mean_absolute_error: 0.2698 - val_loss: 3.5721 - val_mean_absolute_error: 1.4237
Epoch 886/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.2567 - mean_absolute_error: 0.2728 - val_loss: 3.0840 - val_mean_absolute_error: 1.3003
Epoch 887/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2863 - mean_absolute_error: 0.2937 - val_loss: 3.3644 - val_mean_absolute_error: 1.3957
Epoch 888/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2183 - mean_absolute_error: 0.2736 - val_loss: 3.3051 - val_mean_absolute_error: 1.4589
Epoch 889/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1568 - mean_absolute_error: 0.2502 - val_loss: 3.2041 - val_mean_absolute_error: 1.3353
Epoch 890/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0876 - mean_absolute_error: 0.2240 - val_loss: 3.4887 - val_mean_absolute_error: 1.3585
Epoch 891/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1368 - mean_absolute_error: 0.1965 - val_loss: 3.1454 - val_mean_absolute_error: 1.3592
Epoch 892/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1683 - mean_absolute_error: 0.2215 - val_loss: 3.2485 - val_mean_absolute_error: 1.4299
Epoch 893/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0651 - mean_absolute_error: 0.1761 - val_loss: 3.4829 - val_mean_absolute_error: 1.3868
Epoch 894/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0776 - mean_absolute_error: 0.1544 - val_loss: 3.3340 - val_mean_absolute_error: 1.3726
Epoch 895/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0899 - mean_absolute_error: 0.1597 - val_loss: 3.4394 - val_mean_absolute_error: 1.4114
Epoch 896/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0536 - mean_absolute_error: 0.1473 - val_loss: 3.2890 - val_mean_absolute_error: 1.4153
Epoch 897/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0326 - mean_absolute_error: 0.1240 - val_loss: 3.3551 - val_mean_absolute_error: 1.3767
Epoch 898/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0459 - mean_absolute_error: 0.1412 - val_loss: 3.4358 - val_mean_absolute_error: 1.4306
Epoch 899/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1258 - mean_absolute_error: 0.1864 - val_loss: 3.3944 - val_mean_absolute_error: 1.4127
Epoch 900/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1601 - mean_absolute_error: 0.1873 - val_loss: 3.2079 - val_mean_absolute_error: 1.3868
Epoch 901/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1616 - mean_absolute_error: 0.2333 - val_loss: 3.4340 - val_mean_absolute_error: 1.4074
Epoch 902/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.0739 - mean_absolute_error: 0.1772 - val_loss: 3.4423 - val_mean_absolute_error: 1.4727
Epoch 903/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0521 - mean_absolute_error: 0.1610 - val_loss: 3.3384 - val_mean_absolute_error: 1.3471
Epoch 904/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0521 - mean_absolute_error: 0.1573 - val_loss: 3.4068 - val_mean_absolute_error: 1.3970
Epoch 905/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0409 - mean_absolute_error: 0.1599 - val_loss: 3.3435 - val_mean_absolute_error: 1.3302
Epoch 906/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0643 - mean_absolute_error: 0.1578 - val_loss: 3.2479 - val_mean_absolute_error: 1.3930
Epoch 907/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1820 - mean_absolute_error: 0.1742 - val_loss: 3.4338 - val_mean_absolute_error: 1.4335
Epoch 908/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1030 - mean_absolute_error: 0.1966 - val_loss: 3.4274 - val_mean_absolute_error: 1.4130
Epoch 909/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0587 - mean_absolute_error: 0.1665 - val_loss: 3.4722 - val_mean_absolute_error: 1.4473
Epoch 910/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0482 - mean_absolute_error: 0.1557 - val_loss: 3.2392 - val_mean_absolute_error: 1.3515
Epoch 911/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0315 - mean_absolute_error: 0.1326 - val_loss: 3.3417 - val_mean_absolute_error: 1.4406
Epoch 912/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0230 - mean_absolute_error: 0.1113 - val_loss: 3.4077 - val_mean_absolute_error: 1.3573
Epoch 913/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0215 - mean_absolute_error: 0.0896 - val_loss: 3.3183 - val_mean_absolute_error: 1.4480
Epoch 914/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0149 - mean_absolute_error: 0.0818 - val_loss: 3.4104 - val_mean_absolute_error: 1.3603
Epoch 915/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0167 - mean_absolute_error: 0.0905 - val_loss: 3.3721 - val_mean_absolute_error: 1.4241
Epoch 916/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0142 - mean_absolute_error: 0.0695 - val_loss: 3.3919 - val_mean_absolute_error: 1.4049
Epoch 917/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0168 - mean_absolute_error: 0.0707 - val_loss: 3.3781 - val_mean_absolute_error: 1.4323
Epoch 918/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0188 - mean_absolute_error: 0.0765 - val_loss: 3.3871 - val_mean_absolute_error: 1.3758
Epoch 919/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0118 - mean_absolute_error: 0.0733 - val_loss: 3.3872 - val_mean_absolute_error: 1.4375
Epoch 920/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0123 - mean_absolute_error: 0.0711 - val_loss: 3.3493 - val_mean_absolute_error: 1.4045
Epoch 921/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0220 - mean_absolute_error: 0.0804 - val_loss: 3.3731 - val_mean_absolute_error: 1.4225
Epoch 922/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0127 - mean_absolute_error: 0.0747 - val_loss: 3.3932 - val_mean_absolute_error: 1.3963
Epoch 923/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0123 - mean_absolute_error: 0.0767 - val_loss: 3.3119 - val_mean_absolute_error: 1.4203
Epoch 924/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0134 - mean_absolute_error: 0.0808 - val_loss: 3.3382 - val_mean_absolute_error: 1.3717
Epoch 925/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0091 - mean_absolute_error: 0.0680 - val_loss: 3.3871 - val_mean_absolute_error: 1.4249
Epoch 926/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0078 - mean_absolute_error: 0.0595 - val_loss: 3.3753 - val_mean_absolute_error: 1.3873
Epoch 927/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0066 - mean_absolute_error: 0.0519 - val_loss: 3.3763 - val_mean_absolute_error: 1.4361
Epoch 928/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0069 - mean_absolute_error: 0.0566 - val_loss: 3.4029 - val_mean_absolute_error: 1.3914
Epoch 929/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0069 - mean_absolute_error: 0.0542 - val_loss: 3.3659 - val_mean_absolute_error: 1.4101
Epoch 930/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0101 - mean_absolute_error: 0.0548 - val_loss: 3.3366 - val_mean_absolute_error: 1.4086
Epoch 931/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0083 - mean_absolute_error: 0.0570 - val_loss: 3.4155 - val_mean_absolute_error: 1.4180
Epoch 932/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0059 - mean_absolute_error: 0.0540 - val_loss: 3.4060 - val_mean_absolute_error: 1.4242
Epoch 933/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0053 - mean_absolute_error: 0.0479 - val_loss: 3.3854 - val_mean_absolute_error: 1.4032
Epoch 934/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0071 - mean_absolute_error: 0.0483 - val_loss: 3.3615 - val_mean_absolute_error: 1.4380
Epoch 935/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0246 - mean_absolute_error: 0.0780 - val_loss: 3.4734 - val_mean_absolute_error: 1.3825
Epoch 936/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0595 - mean_absolute_error: 0.1144 - val_loss: 3.3416 - val_mean_absolute_error: 1.4357
Epoch 937/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0895 - mean_absolute_error: 0.1373 - val_loss: 3.3891 - val_mean_absolute_error: 1.3950
Epoch 938/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0973 - mean_absolute_error: 0.1300 - val_loss: 3.4647 - val_mean_absolute_error: 1.4436
Epoch 939/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.0562 - mean_absolute_error: 0.1594 - val_loss: 3.2954 - val_mean_absolute_error: 1.3933
Epoch 940/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0718 - mean_absolute_error: 0.1619 - val_loss: 3.6541 - val_mean_absolute_error: 1.4291
Epoch 941/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1425 - mean_absolute_error: 0.2188 - val_loss: 3.3452 - val_mean_absolute_error: 1.4324
Epoch 942/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1479 - mean_absolute_error: 0.2489 - val_loss: 3.2916 - val_mean_absolute_error: 1.3899
Epoch 943/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1190 - mean_absolute_error: 0.2440 - val_loss: 3.5228 - val_mean_absolute_error: 1.3764
Epoch 944/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.0658 - mean_absolute_error: 0.1978 - val_loss: 3.3873 - val_mean_absolute_error: 1.3853
Epoch 945/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0616 - mean_absolute_error: 0.1846 - val_loss: 3.2013 - val_mean_absolute_error: 1.4002
Epoch 946/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0705 - mean_absolute_error: 0.1939 - val_loss: 3.7294 - val_mean_absolute_error: 1.4706
Epoch 947/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0750 - mean_absolute_error: 0.1920 - val_loss: 3.2201 - val_mean_absolute_error: 1.3284
Epoch 948/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0863 - mean_absolute_error: 0.2057 - val_loss: 3.2779 - val_mean_absolute_error: 1.4541
Epoch 949/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4658 - mean_absolute_error: 0.3487 - val_loss: 4.8475 - val_mean_absolute_error: 1.6392
Epoch 950/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5888 - mean_absolute_error: 0.4135 - val_loss: 4.3309 - val_mean_absolute_error: 1.6593
Epoch 951/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4928 - mean_absolute_error: 0.4779 - val_loss: 3.2255 - val_mean_absolute_error: 1.3728
Epoch 952/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.9954 - mean_absolute_error: 0.6388 - val_loss: 3.9038 - val_mean_absolute_error: 1.4606
Epoch 953/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5406 - mean_absolute_error: 0.5210 - val_loss: 2.9882 - val_mean_absolute_error: 1.2346
Epoch 954/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5754 - mean_absolute_error: 0.5263 - val_loss: 3.3033 - val_mean_absolute_error: 1.3420
Epoch 955/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0238 - mean_absolute_error: 0.6273 - val_loss: 4.0075 - val_mean_absolute_error: 1.5460
Epoch 956/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9181 - mean_absolute_error: 0.6162 - val_loss: 3.1060 - val_mean_absolute_error: 1.3435
Epoch 957/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.1824 - mean_absolute_error: 0.6594 - val_loss: 3.4518 - val_mean_absolute_error: 1.4103
Epoch 958/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7798 - mean_absolute_error: 0.6021 - val_loss: 2.6390 - val_mean_absolute_error: 1.2807
Epoch 959/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7088 - mean_absolute_error: 0.5322 - val_loss: 3.5522 - val_mean_absolute_error: 1.4990
Epoch 960/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6707 - mean_absolute_error: 0.5426 - val_loss: 3.1995 - val_mean_absolute_error: 1.3278
Epoch 961/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6753 - mean_absolute_error: 0.5208 - val_loss: 2.6761 - val_mean_absolute_error: 1.3567
Epoch 962/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4454 - mean_absolute_error: 0.4806 - val_loss: 3.2311 - val_mean_absolute_error: 1.3117
Epoch 963/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4210 - mean_absolute_error: 0.4471 - val_loss: 2.8999 - val_mean_absolute_error: 1.3101
Epoch 964/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2786 - mean_absolute_error: 0.3474 - val_loss: 3.1709 - val_mean_absolute_error: 1.3794
Epoch 965/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2667 - mean_absolute_error: 0.3454 - val_loss: 2.8991 - val_mean_absolute_error: 1.3306
Epoch 966/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2326 - mean_absolute_error: 0.3007 - val_loss: 2.8820 - val_mean_absolute_error: 1.2846
Epoch 967/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2783 - mean_absolute_error: 0.3369 - val_loss: 2.7321 - val_mean_absolute_error: 1.2322
Epoch 968/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2635 - mean_absolute_error: 0.3017 - val_loss: 3.1345 - val_mean_absolute_error: 1.3162
Epoch 969/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1997 - mean_absolute_error: 0.2635 - val_loss: 2.8648 - val_mean_absolute_error: 1.2910
Epoch 970/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1773 - mean_absolute_error: 0.2559 - val_loss: 3.0663 - val_mean_absolute_error: 1.2924
Epoch 971/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1311 - mean_absolute_error: 0.2150 - val_loss: 2.9195 - val_mean_absolute_error: 1.3297
Epoch 972/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1011 - mean_absolute_error: 0.1777 - val_loss: 3.0992 - val_mean_absolute_error: 1.3496
Epoch 973/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1133 - mean_absolute_error: 0.1717 - val_loss: 3.0232 - val_mean_absolute_error: 1.3566
Epoch 974/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1035 - mean_absolute_error: 0.1758 - val_loss: 3.1432 - val_mean_absolute_error: 1.3257
Epoch 975/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0785 - mean_absolute_error: 0.1427 - val_loss: 3.1139 - val_mean_absolute_error: 1.3403
Epoch 976/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0762 - mean_absolute_error: 0.1221 - val_loss: 3.0890 - val_mean_absolute_error: 1.3407
Epoch 977/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.0850 - mean_absolute_error: 0.1352 - val_loss: 3.1377 - val_mean_absolute_error: 1.3688
Epoch 978/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0744 - mean_absolute_error: 0.1295 - val_loss: 3.1110 - val_mean_absolute_error: 1.3280
Epoch 979/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0729 - mean_absolute_error: 0.1258 - val_loss: 3.1838 - val_mean_absolute_error: 1.3568
Epoch 980/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0785 - mean_absolute_error: 0.1407 - val_loss: 3.0942 - val_mean_absolute_error: 1.3487
Epoch 981/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0786 - mean_absolute_error: 0.1400 - val_loss: 3.1059 - val_mean_absolute_error: 1.3282
Epoch 982/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0853 - mean_absolute_error: 0.1465 - val_loss: 3.2510 - val_mean_absolute_error: 1.3781
Epoch 983/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0742 - mean_absolute_error: 0.1607 - val_loss: 3.1160 - val_mean_absolute_error: 1.3480
Epoch 984/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0688 - mean_absolute_error: 0.1536 - val_loss: 3.2291 - val_mean_absolute_error: 1.3736
Epoch 985/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0768 - mean_absolute_error: 0.1530 - val_loss: 3.1709 - val_mean_absolute_error: 1.3761
Epoch 986/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0814 - mean_absolute_error: 0.1515 - val_loss: 3.2049 - val_mean_absolute_error: 1.3784
Epoch 987/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.0720 - mean_absolute_error: 0.1372 - val_loss: 3.2771 - val_mean_absolute_error: 1.3727
Epoch 988/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.0702 - mean_absolute_error: 0.1439 - val_loss: 3.1808 - val_mean_absolute_error: 1.3608
Epoch 989/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0617 - mean_absolute_error: 0.1309 - val_loss: 3.1763 - val_mean_absolute_error: 1.3491
Epoch 990/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0735 - mean_absolute_error: 0.1284 - val_loss: 3.2107 - val_mean_absolute_error: 1.3794
Epoch 991/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.0509 - mean_absolute_error: 0.1204 - val_loss: 3.2211 - val_mean_absolute_error: 1.3451
Epoch 992/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.0673 - mean_absolute_error: 0.1241 - val_loss: 3.2432 - val_mean_absolute_error: 1.4029
Epoch 993/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.0488 - mean_absolute_error: 0.1149 - val_loss: 3.2763 - val_mean_absolute_error: 1.3269
Epoch 994/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.0518 - mean_absolute_error: 0.1210 - val_loss: 3.2600 - val_mean_absolute_error: 1.3970
Epoch 995/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0525 - mean_absolute_error: 0.1193 - val_loss: 3.2149 - val_mean_absolute_error: 1.3469
Epoch 996/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0440 - mean_absolute_error: 0.1184 - val_loss: 3.1814 - val_mean_absolute_error: 1.3793
Epoch 997/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0523 - mean_absolute_error: 0.1318 - val_loss: 3.3480 - val_mean_absolute_error: 1.3778
Epoch 998/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0711 - mean_absolute_error: 0.1192 - val_loss: 3.3750 - val_mean_absolute_error: 1.3978
Epoch 999/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0999 - mean_absolute_error: 0.1588 - val_loss: 3.1819 - val_mean_absolute_error: 1.3655
Epoch 1000/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0611 - mean_absolute_error: 0.1591 - val_loss: 3.2781 - val_mean_absolute_error: 1.3418
7/7 [==============================] - 1s 5ms/step
1/1 [==============================] - 0s 20ms/step
1/1 [==============================] - 0s 21ms/step

# Calculate the RMSE
rmse_lstm = sqrt(mean_squared_error(y_test_DBK, test_predictions_DBK))
print('The RMSE value of LSTM model (DBK): {:.4f}'.format(rmse_lstm))

The RMSE value of LSTM model (DBK): 2.6075

# Plot Training Observations VS Training Predictions 
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_train_DBK, train_predictions_DBK)
plt.plot(dates_train_DBK, y_train_DBK)
plt.title('LSTM: Training Actual Returns/Training Predicted Returns (DBK)', fontsize=16)
plt.legend(['DBK Training Predictions', 'DBK Training Observations'])

# Plot Testing Observations VS Testing Predictions 
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_test_DBK, test_predictions_DBK)
plt.plot(dates_test_DBK, y_test_DBK)
plt.title('LSTM: Testing Actual Returns/Testing Predicted Returns (DBK)', fontsize=16)
plt.legend(['DBK Testing Predictions', 'DBK Testing Observations'])

# General Plot (Training, Validation & testing)
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_train_DBK, train_predictions_DBK)
plt.plot(dates_train_DBK, y_train_DBK)
plt.plot(dates_val_DBK, val_predictions_DBK)
plt.plot(dates_val_DBK, y_val_DBK)
plt.plot(dates_test_DBK, test_predictions_DBK)
plt.plot(dates_test_DBK, y_test_DBK)
plt.title('LSTM: General forecasting plot (DBK)', fontsize=16)
plt.legend(['DBK Training Predictions', 
            'DBK Training Observations',
            'DBK Validation Predictions', 
            'DBK Validation Observations',
            'DBK Testing Predictions', 
            'DBK Testing Observations'])

<matplotlib.legend.Legend at 0x7fa8c6366460>

Bank of America Corp

# transform a time series dataset into a supervised learning dataset (Input : Output)
def BAC_to_windowed_BAC(BAC_RET, first_date_str, last_date_str, n=3):
    first_date = str_to_datetime(first_date_str)
    last_date  = str_to_datetime(last_date_str)
    
    target_date = first_date
    
    dates_BAC = []
    X, Y = [], []
    
    last_time = False
    while True:
        BAC_subset = BAC_RET.loc[:target_date].tail(n+1)
        
        if len(BAC_subset) != n+1:
            print(f'Error: Window of size {n} is too large for date {target_date}')
            return
        
        values = BAC_subset['Ret_BAC'].to_numpy()
        x, y = values[:-1], values[-1]
        
        dates_BAC.append(target_date)
        X.append(x)
        Y.append(y)
        
        next_week = BAC_RET.loc[target_date:target_date+datetime.timedelta(days=7)]
        next_datetime_str = str(next_week.head(2).tail(1).index.values[0])
        next_date_str = next_datetime_str.split('T')[0]
        year_month_day = next_date_str.split('-')
        year, month, day = year_month_day
        next_date = datetime.datetime(day=int(day), month=int(month), year=int(year))
        
        if last_time:
            break
        
        target_date = next_date
        
        if target_date == last_date:
            last_time = True
    ret_BAC = pd.DataFrame({})
    ret_BAC['Target Date'] = dates_BAC
    
    X = np.array(X)
    for i in range(0, n):
        X[:, i]
        ret_BAC[f'Target-{n-i}'] = X[:, i]
        
    ret_BAC['Target'] = Y
    
    return ret_BAC

# Start day second time around: '2020-01-03'
windowed_BAC = BAC_to_windowed_BAC(BAC_RET, 
                                '2020-01-03', 
                                '2020-12-30', 
                                n=3)

# Convert our new dataset into numpy arrays (to feed it directly into a tensorflow model)
def windowed_BAC_to_date_X_y(windowed_dataframe):
    BAC_as_np = windowed_dataframe.to_numpy()
    
    dates_BAC = BAC_as_np[:, 0] 
    
    middle_matrix_BAC = BAC_as_np[:, 1:-1]
    X_BAC = middle_matrix_BAC.reshape((len(dates_BAC), middle_matrix_BAC.shape[1], 1))
    
    Y_BAC = BAC_as_np[:, -1]
    
    return dates_BAC, X_BAC.astype(np.float32), Y_BAC.astype(np.float32)

dates_BAC, X_BAC, y_BAC = windowed_BAC_to_date_X_y(windowed_BAC)

# Split the data into training, validation and testing partitions 
q_85_BAC = int(len(dates_BAC) * .85)
q_95_BAC = int(len(dates_BAC) * .95)

dates_train_BAC, X_train_BAC, y_train_BAC = dates_BAC[:q_85_BAC], X_BAC[:q_85_BAC], y_BAC[:q_85_BAC]
dates_val_BAC, X_val_BAC, y_val_BAC = dates_BAC[q_85_BAC:q_95_BAC], X_BAC[q_85_BAC:q_95_BAC], y_BAC[q_85_BAC:q_95_BAC]
dates_test_BAC, X_test_BAC, y_test_BAC = dates_BAC[q_95_BAC:], X_BAC[q_95_BAC:], y_BAC[q_95_BAC:]

# Create & train the LSTM model 
model_BAC = Sequential([layers.Input((3, 1)),
                    layers.LSTM(264),
                    layers.Dense(132, activation='relu'),
                    layers.Dense(132, activation='relu'),
                    layers.Dense(1)])

model_BAC.compile(loss='mse', 
              optimizer=Adam(learning_rate=0.001),
              metrics=['mean_absolute_error'])

# Fitting the LSTM model 
model_BAC.fit(X_train_BAC, y_train_BAC, validation_data=(X_val_BAC, y_val_BAC), epochs=1000)

# Forecasting
train_predictions_BAC = model_BAC.predict(X_train_BAC).flatten()
val_predictions_BAC = model_BAC.predict(X_val_BAC).flatten()
test_predictions_BAC = model_BAC.predict(X_test_BAC).flatten()

Epoch 1/1000
7/7 [==============================] - 3s 112ms/step - loss: 14.8813 - mean_absolute_error: 2.6239 - val_loss: 11.5781 - val_mean_absolute_error: 2.0382
Epoch 2/1000
7/7 [==============================] - 0s 27ms/step - loss: 14.6534 - mean_absolute_error: 2.6105 - val_loss: 11.5078 - val_mean_absolute_error: 2.0286
Epoch 3/1000
7/7 [==============================] - 0s 22ms/step - loss: 14.4296 - mean_absolute_error: 2.5985 - val_loss: 11.5756 - val_mean_absolute_error: 2.0346
Epoch 4/1000
7/7 [==============================] - 0s 28ms/step - loss: 14.2191 - mean_absolute_error: 2.5901 - val_loss: 11.6671 - val_mean_absolute_error: 2.0499
Epoch 5/1000
7/7 [==============================] - 0s 26ms/step - loss: 13.9118 - mean_absolute_error: 2.5715 - val_loss: 11.7387 - val_mean_absolute_error: 2.0607
Epoch 6/1000
7/7 [==============================] - 0s 25ms/step - loss: 13.8642 - mean_absolute_error: 2.5603 - val_loss: 11.8101 - val_mean_absolute_error: 2.0657
Epoch 7/1000
7/7 [==============================] - 0s 35ms/step - loss: 13.4273 - mean_absolute_error: 2.5315 - val_loss: 11.6730 - val_mean_absolute_error: 2.0615
Epoch 8/1000
7/7 [==============================] - 0s 28ms/step - loss: 13.2265 - mean_absolute_error: 2.5258 - val_loss: 11.7576 - val_mean_absolute_error: 2.0627
Epoch 9/1000
7/7 [==============================] - 0s 19ms/step - loss: 12.9080 - mean_absolute_error: 2.5118 - val_loss: 11.4892 - val_mean_absolute_error: 2.0149
Epoch 10/1000
7/7 [==============================] - 0s 19ms/step - loss: 12.5856 - mean_absolute_error: 2.4830 - val_loss: 11.4736 - val_mean_absolute_error: 2.0085
Epoch 11/1000
7/7 [==============================] - 0s 20ms/step - loss: 12.2060 - mean_absolute_error: 2.4365 - val_loss: 11.4389 - val_mean_absolute_error: 2.0537
Epoch 12/1000
7/7 [==============================] - 0s 18ms/step - loss: 11.8953 - mean_absolute_error: 2.4164 - val_loss: 11.3391 - val_mean_absolute_error: 2.0719
Epoch 13/1000
7/7 [==============================] - 0s 20ms/step - loss: 11.5447 - mean_absolute_error: 2.4005 - val_loss: 11.4233 - val_mean_absolute_error: 2.0950
Epoch 14/1000
7/7 [==============================] - 0s 19ms/step - loss: 11.4386 - mean_absolute_error: 2.4208 - val_loss: 12.0177 - val_mean_absolute_error: 2.1977
Epoch 15/1000
7/7 [==============================] - 0s 19ms/step - loss: 11.0429 - mean_absolute_error: 2.3897 - val_loss: 12.0790 - val_mean_absolute_error: 2.2140
Epoch 16/1000
7/7 [==============================] - 0s 19ms/step - loss: 11.2179 - mean_absolute_error: 2.3695 - val_loss: 12.0721 - val_mean_absolute_error: 2.2639
Epoch 17/1000
7/7 [==============================] - 0s 22ms/step - loss: 10.7122 - mean_absolute_error: 2.3275 - val_loss: 12.1177 - val_mean_absolute_error: 2.2553
Epoch 18/1000
7/7 [==============================] - 0s 21ms/step - loss: 10.2804 - mean_absolute_error: 2.3120 - val_loss: 12.6052 - val_mean_absolute_error: 2.3578
Epoch 19/1000
7/7 [==============================] - 0s 22ms/step - loss: 9.9589 - mean_absolute_error: 2.3078 - val_loss: 12.7466 - val_mean_absolute_error: 2.4293
Epoch 20/1000
7/7 [==============================] - 0s 23ms/step - loss: 9.9819 - mean_absolute_error: 2.3017 - val_loss: 12.6230 - val_mean_absolute_error: 2.4351
Epoch 21/1000
7/7 [==============================] - 0s 22ms/step - loss: 9.8971 - mean_absolute_error: 2.3255 - val_loss: 13.0911 - val_mean_absolute_error: 2.4848
Epoch 22/1000
7/7 [==============================] - 0s 25ms/step - loss: 9.6080 - mean_absolute_error: 2.2780 - val_loss: 13.0307 - val_mean_absolute_error: 2.4966
Epoch 23/1000
7/7 [==============================] - 0s 21ms/step - loss: 9.3405 - mean_absolute_error: 2.2707 - val_loss: 13.2750 - val_mean_absolute_error: 2.5559
Epoch 24/1000
7/7 [==============================] - 0s 32ms/step - loss: 9.8356 - mean_absolute_error: 2.3163 - val_loss: 12.7779 - val_mean_absolute_error: 2.4845
Epoch 25/1000
7/7 [==============================] - 0s 24ms/step - loss: 9.0594 - mean_absolute_error: 2.2088 - val_loss: 12.2023 - val_mean_absolute_error: 2.3686
Epoch 26/1000
7/7 [==============================] - 0s 25ms/step - loss: 9.6780 - mean_absolute_error: 2.3192 - val_loss: 12.4346 - val_mean_absolute_error: 2.3908
Epoch 27/1000
7/7 [==============================] - 0s 29ms/step - loss: 9.3994 - mean_absolute_error: 2.2923 - val_loss: 12.1354 - val_mean_absolute_error: 2.4508
Epoch 28/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.8461 - mean_absolute_error: 2.2214 - val_loss: 13.0585 - val_mean_absolute_error: 2.5838
Epoch 29/1000
7/7 [==============================] - 0s 20ms/step - loss: 8.7222 - mean_absolute_error: 2.1987 - val_loss: 13.3275 - val_mean_absolute_error: 2.6238
Epoch 30/1000
7/7 [==============================] - 0s 18ms/step - loss: 8.6088 - mean_absolute_error: 2.1958 - val_loss: 13.1153 - val_mean_absolute_error: 2.5993
Epoch 31/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.5868 - mean_absolute_error: 2.2198 - val_loss: 13.1791 - val_mean_absolute_error: 2.5613
Epoch 32/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.3970 - mean_absolute_error: 2.1801 - val_loss: 13.3865 - val_mean_absolute_error: 2.6686
Epoch 33/1000
7/7 [==============================] - 0s 18ms/step - loss: 8.3322 - mean_absolute_error: 2.1922 - val_loss: 14.2853 - val_mean_absolute_error: 2.7578
Epoch 34/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.5778 - mean_absolute_error: 2.2449 - val_loss: 14.3613 - val_mean_absolute_error: 2.7252
Epoch 35/1000
7/7 [==============================] - 0s 20ms/step - loss: 8.5648 - mean_absolute_error: 2.1448 - val_loss: 12.6172 - val_mean_absolute_error: 2.5391
Epoch 36/1000
7/7 [==============================] - 0s 20ms/step - loss: 8.6007 - mean_absolute_error: 2.2286 - val_loss: 12.9621 - val_mean_absolute_error: 2.5480
Epoch 37/1000
7/7 [==============================] - 0s 17ms/step - loss: 8.2745 - mean_absolute_error: 2.2074 - val_loss: 13.6414 - val_mean_absolute_error: 2.6717
Epoch 38/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.9280 - mean_absolute_error: 2.2118 - val_loss: 13.9346 - val_mean_absolute_error: 2.7181
Epoch 39/1000
7/7 [==============================] - 0s 20ms/step - loss: 8.1288 - mean_absolute_error: 2.1669 - val_loss: 12.9274 - val_mean_absolute_error: 2.5728
Epoch 40/1000
7/7 [==============================] - 0s 21ms/step - loss: 8.3352 - mean_absolute_error: 2.1636 - val_loss: 13.7995 - val_mean_absolute_error: 2.6585
Epoch 41/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.1495 - mean_absolute_error: 2.1782 - val_loss: 13.7854 - val_mean_absolute_error: 2.7026
Epoch 42/1000
7/7 [==============================] - 0s 20ms/step - loss: 7.7530 - mean_absolute_error: 2.1205 - val_loss: 12.8499 - val_mean_absolute_error: 2.6092
Epoch 43/1000
7/7 [==============================] - 0s 20ms/step - loss: 7.7149 - mean_absolute_error: 2.1191 - val_loss: 12.8244 - val_mean_absolute_error: 2.5987
Epoch 44/1000
7/7 [==============================] - 0s 20ms/step - loss: 7.5152 - mean_absolute_error: 2.0885 - val_loss: 13.4312 - val_mean_absolute_error: 2.6633
Epoch 45/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.4450 - mean_absolute_error: 2.0592 - val_loss: 12.9214 - val_mean_absolute_error: 2.5876
Epoch 46/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.5790 - mean_absolute_error: 2.0968 - val_loss: 13.8606 - val_mean_absolute_error: 2.6019
Epoch 47/1000
7/7 [==============================] - 0s 21ms/step - loss: 7.3632 - mean_absolute_error: 2.0529 - val_loss: 13.6520 - val_mean_absolute_error: 2.6548
Epoch 48/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.2112 - mean_absolute_error: 2.0358 - val_loss: 13.7063 - val_mean_absolute_error: 2.6593
Epoch 49/1000
7/7 [==============================] - 0s 20ms/step - loss: 7.3133 - mean_absolute_error: 2.0316 - val_loss: 13.5666 - val_mean_absolute_error: 2.6369
Epoch 50/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.5064 - mean_absolute_error: 2.0835 - val_loss: 13.6609 - val_mean_absolute_error: 2.6386
Epoch 51/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.1798 - mean_absolute_error: 2.0579 - val_loss: 13.3694 - val_mean_absolute_error: 2.6484
Epoch 52/1000
7/7 [==============================] - 0s 25ms/step - loss: 6.9799 - mean_absolute_error: 2.0222 - val_loss: 13.2812 - val_mean_absolute_error: 2.6340
Epoch 53/1000
7/7 [==============================] - 0s 22ms/step - loss: 6.9118 - mean_absolute_error: 2.0250 - val_loss: 12.9059 - val_mean_absolute_error: 2.5691
Epoch 54/1000
7/7 [==============================] - 0s 21ms/step - loss: 7.1676 - mean_absolute_error: 2.0267 - val_loss: 13.5148 - val_mean_absolute_error: 2.6641
Epoch 55/1000
7/7 [==============================] - 0s 20ms/step - loss: 7.1956 - mean_absolute_error: 2.0657 - val_loss: 13.4750 - val_mean_absolute_error: 2.6564
Epoch 56/1000
7/7 [==============================] - 0s 21ms/step - loss: 6.9404 - mean_absolute_error: 2.0292 - val_loss: 12.4637 - val_mean_absolute_error: 2.5340
Epoch 57/1000
7/7 [==============================] - 0s 20ms/step - loss: 6.6481 - mean_absolute_error: 1.9787 - val_loss: 13.5392 - val_mean_absolute_error: 2.6591
Epoch 58/1000
7/7 [==============================] - 0s 20ms/step - loss: 6.7077 - mean_absolute_error: 1.9676 - val_loss: 13.3153 - val_mean_absolute_error: 2.6415
Epoch 59/1000
7/7 [==============================] - 0s 20ms/step - loss: 6.9432 - mean_absolute_error: 1.9795 - val_loss: 12.6939 - val_mean_absolute_error: 2.5570
Epoch 60/1000
7/7 [==============================] - 0s 21ms/step - loss: 6.4665 - mean_absolute_error: 1.9373 - val_loss: 12.5153 - val_mean_absolute_error: 2.5304
Epoch 61/1000
7/7 [==============================] - 0s 20ms/step - loss: 6.4330 - mean_absolute_error: 1.9413 - val_loss: 12.8138 - val_mean_absolute_error: 2.5774
Epoch 62/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.3206 - mean_absolute_error: 1.9300 - val_loss: 12.9154 - val_mean_absolute_error: 2.5903
Epoch 63/1000
7/7 [==============================] - 0s 18ms/step - loss: 6.4127 - mean_absolute_error: 1.9279 - val_loss: 12.9949 - val_mean_absolute_error: 2.6018
Epoch 64/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.3367 - mean_absolute_error: 1.9524 - val_loss: 12.8087 - val_mean_absolute_error: 2.5932
Epoch 65/1000
7/7 [==============================] - 0s 20ms/step - loss: 6.0177 - mean_absolute_error: 1.8647 - val_loss: 12.4370 - val_mean_absolute_error: 2.5424
Epoch 66/1000
7/7 [==============================] - 0s 20ms/step - loss: 6.0295 - mean_absolute_error: 1.8827 - val_loss: 13.0858 - val_mean_absolute_error: 2.5805
Epoch 67/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.0200 - mean_absolute_error: 1.8924 - val_loss: 12.5223 - val_mean_absolute_error: 2.5599
Epoch 68/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.2355 - mean_absolute_error: 1.9369 - val_loss: 12.5230 - val_mean_absolute_error: 2.5688
Epoch 69/1000
7/7 [==============================] - 0s 20ms/step - loss: 5.9939 - mean_absolute_error: 1.8999 - val_loss: 11.9174 - val_mean_absolute_error: 2.5036
Epoch 70/1000
7/7 [==============================] - 0s 18ms/step - loss: 6.2333 - mean_absolute_error: 1.9152 - val_loss: 12.5639 - val_mean_absolute_error: 2.5336
Epoch 71/1000
7/7 [==============================] - 0s 20ms/step - loss: 5.9608 - mean_absolute_error: 1.9058 - val_loss: 11.9151 - val_mean_absolute_error: 2.4753
Epoch 72/1000
7/7 [==============================] - 0s 20ms/step - loss: 5.7915 - mean_absolute_error: 1.8698 - val_loss: 12.1622 - val_mean_absolute_error: 2.4977
Epoch 73/1000
7/7 [==============================] - 0s 20ms/step - loss: 5.8869 - mean_absolute_error: 1.8727 - val_loss: 12.6293 - val_mean_absolute_error: 2.5824
Epoch 74/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.6479 - mean_absolute_error: 1.8336 - val_loss: 12.4103 - val_mean_absolute_error: 2.5291
Epoch 75/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.5389 - mean_absolute_error: 1.8019 - val_loss: 12.4918 - val_mean_absolute_error: 2.5490
Epoch 76/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.5037 - mean_absolute_error: 1.7902 - val_loss: 12.2234 - val_mean_absolute_error: 2.5171
Epoch 77/1000
7/7 [==============================] - 0s 30ms/step - loss: 5.3361 - mean_absolute_error: 1.7709 - val_loss: 11.7449 - val_mean_absolute_error: 2.5298
Epoch 78/1000
7/7 [==============================] - 0s 32ms/step - loss: 5.6037 - mean_absolute_error: 1.7962 - val_loss: 11.9822 - val_mean_absolute_error: 2.5774
Epoch 79/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.3602 - mean_absolute_error: 1.7742 - val_loss: 11.9361 - val_mean_absolute_error: 2.4989
Epoch 80/1000
7/7 [==============================] - 0s 20ms/step - loss: 5.2399 - mean_absolute_error: 1.7712 - val_loss: 11.6439 - val_mean_absolute_error: 2.5057
Epoch 81/1000
7/7 [==============================] - 0s 20ms/step - loss: 5.1381 - mean_absolute_error: 1.7544 - val_loss: 11.3065 - val_mean_absolute_error: 2.4537
Epoch 82/1000
7/7 [==============================] - 0s 21ms/step - loss: 5.0918 - mean_absolute_error: 1.7371 - val_loss: 11.4851 - val_mean_absolute_error: 2.4708
Epoch 83/1000
7/7 [==============================] - 0s 22ms/step - loss: 5.0986 - mean_absolute_error: 1.7476 - val_loss: 11.9352 - val_mean_absolute_error: 2.5383
Epoch 84/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.9459 - mean_absolute_error: 1.6753 - val_loss: 11.6300 - val_mean_absolute_error: 2.5563
Epoch 85/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.8896 - mean_absolute_error: 1.7087 - val_loss: 10.7460 - val_mean_absolute_error: 2.4513
Epoch 86/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.8507 - mean_absolute_error: 1.7050 - val_loss: 11.0260 - val_mean_absolute_error: 2.4433
Epoch 87/1000
7/7 [==============================] - 0s 20ms/step - loss: 5.0051 - mean_absolute_error: 1.7133 - val_loss: 11.5852 - val_mean_absolute_error: 2.4998
Epoch 88/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.4793 - mean_absolute_error: 1.8046 - val_loss: 12.5219 - val_mean_absolute_error: 2.5568
Epoch 89/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.7628 - mean_absolute_error: 1.8615 - val_loss: 9.7364 - val_mean_absolute_error: 2.3440
Epoch 90/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.5944 - mean_absolute_error: 1.8338 - val_loss: 11.8754 - val_mean_absolute_error: 2.5606
Epoch 91/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.6178 - mean_absolute_error: 1.8196 - val_loss: 10.9497 - val_mean_absolute_error: 2.4340
Epoch 92/1000
7/7 [==============================] - 0s 20ms/step - loss: 5.5146 - mean_absolute_error: 1.8293 - val_loss: 10.6790 - val_mean_absolute_error: 2.4603
Epoch 93/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.6105 - mean_absolute_error: 1.6473 - val_loss: 12.1407 - val_mean_absolute_error: 2.5807
Epoch 94/1000
7/7 [==============================] - 0s 20ms/step - loss: 5.1948 - mean_absolute_error: 1.7687 - val_loss: 11.6685 - val_mean_absolute_error: 2.5115
Epoch 95/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.5866 - mean_absolute_error: 1.6849 - val_loss: 11.0601 - val_mean_absolute_error: 2.4803
Epoch 96/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.4828 - mean_absolute_error: 1.6494 - val_loss: 10.8231 - val_mean_absolute_error: 2.4823
Epoch 97/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.3043 - mean_absolute_error: 1.6054 - val_loss: 10.7673 - val_mean_absolute_error: 2.4655
Epoch 98/1000
7/7 [==============================] - 0s 21ms/step - loss: 4.2071 - mean_absolute_error: 1.5734 - val_loss: 11.0957 - val_mean_absolute_error: 2.4978
Epoch 99/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.1250 - mean_absolute_error: 1.5686 - val_loss: 11.7161 - val_mean_absolute_error: 2.5094
Epoch 100/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.1819 - mean_absolute_error: 1.5800 - val_loss: 11.5696 - val_mean_absolute_error: 2.4679
Epoch 101/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.4452 - mean_absolute_error: 1.6348 - val_loss: 11.4281 - val_mean_absolute_error: 2.5224
Epoch 102/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.2608 - mean_absolute_error: 1.6072 - val_loss: 11.8305 - val_mean_absolute_error: 2.5927
Epoch 103/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.0654 - mean_absolute_error: 1.5851 - val_loss: 11.6524 - val_mean_absolute_error: 2.6053
Epoch 104/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.9834 - mean_absolute_error: 1.5630 - val_loss: 12.4531 - val_mean_absolute_error: 2.6173
Epoch 105/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.8692 - mean_absolute_error: 1.5471 - val_loss: 11.3603 - val_mean_absolute_error: 2.5560
Epoch 106/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.0440 - mean_absolute_error: 1.5686 - val_loss: 11.9171 - val_mean_absolute_error: 2.5597
Epoch 107/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.9703 - mean_absolute_error: 1.5524 - val_loss: 12.3524 - val_mean_absolute_error: 2.6150
Epoch 108/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.8778 - mean_absolute_error: 1.5254 - val_loss: 11.2249 - val_mean_absolute_error: 2.5648
Epoch 109/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.0221 - mean_absolute_error: 1.5761 - val_loss: 12.2646 - val_mean_absolute_error: 2.6097
Epoch 110/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.0490 - mean_absolute_error: 1.5504 - val_loss: 11.5389 - val_mean_absolute_error: 2.6096
Epoch 111/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.8138 - mean_absolute_error: 1.5301 - val_loss: 12.1342 - val_mean_absolute_error: 2.5970
Epoch 112/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.1622 - mean_absolute_error: 1.5750 - val_loss: 13.2667 - val_mean_absolute_error: 2.7071
Epoch 113/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.0885 - mean_absolute_error: 1.5672 - val_loss: 11.6533 - val_mean_absolute_error: 2.5721
Epoch 114/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.7525 - mean_absolute_error: 1.5201 - val_loss: 12.5285 - val_mean_absolute_error: 2.7109
Epoch 115/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.8603 - mean_absolute_error: 1.5266 - val_loss: 11.6242 - val_mean_absolute_error: 2.5741
Epoch 116/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.7306 - mean_absolute_error: 1.5031 - val_loss: 13.3945 - val_mean_absolute_error: 2.7457
Epoch 117/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.5558 - mean_absolute_error: 1.4591 - val_loss: 11.4685 - val_mean_absolute_error: 2.6445
Epoch 118/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.3474 - mean_absolute_error: 1.4045 - val_loss: 13.1111 - val_mean_absolute_error: 2.7328
Epoch 119/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.6341 - mean_absolute_error: 1.4573 - val_loss: 11.9714 - val_mean_absolute_error: 2.6572
Epoch 120/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.7191 - mean_absolute_error: 1.5119 - val_loss: 10.8905 - val_mean_absolute_error: 2.5671
Epoch 121/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.8713 - mean_absolute_error: 1.5122 - val_loss: 14.0087 - val_mean_absolute_error: 2.7923
Epoch 122/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.4481 - mean_absolute_error: 1.4297 - val_loss: 12.9009 - val_mean_absolute_error: 2.7341
Epoch 123/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.3946 - mean_absolute_error: 1.4364 - val_loss: 11.7029 - val_mean_absolute_error: 2.6106
Epoch 124/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.4883 - mean_absolute_error: 1.4088 - val_loss: 12.5829 - val_mean_absolute_error: 2.7128
Epoch 125/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.4001 - mean_absolute_error: 1.3724 - val_loss: 12.1939 - val_mean_absolute_error: 2.7021
Epoch 126/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.4151 - mean_absolute_error: 1.3940 - val_loss: 12.0603 - val_mean_absolute_error: 2.6669
Epoch 127/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.1184 - mean_absolute_error: 1.3674 - val_loss: 11.7343 - val_mean_absolute_error: 2.6246
Epoch 128/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.3976 - mean_absolute_error: 1.3961 - val_loss: 12.6104 - val_mean_absolute_error: 2.7089
Epoch 129/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.5491 - mean_absolute_error: 1.3879 - val_loss: 11.7930 - val_mean_absolute_error: 2.6915
Epoch 130/1000
7/7 [==============================] - 0s 30ms/step - loss: 3.7652 - mean_absolute_error: 1.4397 - val_loss: 12.7435 - val_mean_absolute_error: 2.7260
Epoch 131/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.1672 - mean_absolute_error: 1.3300 - val_loss: 12.3652 - val_mean_absolute_error: 2.6534
Epoch 132/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.0748 - mean_absolute_error: 1.3445 - val_loss: 12.4414 - val_mean_absolute_error: 2.6567
Epoch 133/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.0797 - mean_absolute_error: 1.3099 - val_loss: 13.5403 - val_mean_absolute_error: 2.7910
Epoch 134/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.0331 - mean_absolute_error: 1.3318 - val_loss: 12.1799 - val_mean_absolute_error: 2.7048
Epoch 135/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.8836 - mean_absolute_error: 1.2769 - val_loss: 12.9637 - val_mean_absolute_error: 2.7898
Epoch 136/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.8331 - mean_absolute_error: 1.2675 - val_loss: 12.7286 - val_mean_absolute_error: 2.7376
Epoch 137/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.8881 - mean_absolute_error: 1.2839 - val_loss: 13.4722 - val_mean_absolute_error: 2.7826
Epoch 138/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.8206 - mean_absolute_error: 1.2756 - val_loss: 12.2125 - val_mean_absolute_error: 2.6902
Epoch 139/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.9885 - mean_absolute_error: 1.2627 - val_loss: 12.3354 - val_mean_absolute_error: 2.7162
Epoch 140/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.8023 - mean_absolute_error: 1.2209 - val_loss: 12.9204 - val_mean_absolute_error: 2.7832
Epoch 141/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.6619 - mean_absolute_error: 1.2111 - val_loss: 12.4418 - val_mean_absolute_error: 2.6655
Epoch 142/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.8507 - mean_absolute_error: 1.2399 - val_loss: 14.4104 - val_mean_absolute_error: 2.8638
Epoch 143/1000
7/7 [==============================] - 0s 21ms/step - loss: 3.0199 - mean_absolute_error: 1.2940 - val_loss: 13.8784 - val_mean_absolute_error: 2.7768
Epoch 144/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.2883 - mean_absolute_error: 1.3526 - val_loss: 11.9637 - val_mean_absolute_error: 2.5752
Epoch 145/1000
7/7 [==============================] - 0s 22ms/step - loss: 3.4011 - mean_absolute_error: 1.3674 - val_loss: 13.4032 - val_mean_absolute_error: 2.8923
Epoch 146/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.3570 - mean_absolute_error: 1.3161 - val_loss: 12.6101 - val_mean_absolute_error: 2.8191
Epoch 147/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.0590 - mean_absolute_error: 1.2918 - val_loss: 12.1756 - val_mean_absolute_error: 2.6564
Epoch 148/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.7857 - mean_absolute_error: 1.2836 - val_loss: 12.9471 - val_mean_absolute_error: 2.7466
Epoch 149/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.6422 - mean_absolute_error: 1.2116 - val_loss: 11.1142 - val_mean_absolute_error: 2.6027
Epoch 150/1000
7/7 [==============================] - 0s 30ms/step - loss: 2.6248 - mean_absolute_error: 1.2050 - val_loss: 11.9937 - val_mean_absolute_error: 2.7385
Epoch 151/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5421 - mean_absolute_error: 1.1645 - val_loss: 12.4640 - val_mean_absolute_error: 2.7042
Epoch 152/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.7422 - mean_absolute_error: 1.2409 - val_loss: 13.2452 - val_mean_absolute_error: 2.7613
Epoch 153/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5027 - mean_absolute_error: 1.1782 - val_loss: 12.2873 - val_mean_absolute_error: 2.7067
Epoch 154/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4517 - mean_absolute_error: 1.1412 - val_loss: 13.3298 - val_mean_absolute_error: 2.8262
Epoch 155/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.3415 - mean_absolute_error: 1.1131 - val_loss: 13.5745 - val_mean_absolute_error: 2.8647
Epoch 156/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.5749 - mean_absolute_error: 1.2094 - val_loss: 12.8705 - val_mean_absolute_error: 2.6524
Epoch 157/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5554 - mean_absolute_error: 1.2186 - val_loss: 13.2883 - val_mean_absolute_error: 2.7331
Epoch 158/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.3598 - mean_absolute_error: 1.1550 - val_loss: 12.3002 - val_mean_absolute_error: 2.7021
Epoch 159/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4637 - mean_absolute_error: 1.1801 - val_loss: 12.6783 - val_mean_absolute_error: 2.7151
Epoch 160/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5383 - mean_absolute_error: 1.1939 - val_loss: 13.9599 - val_mean_absolute_error: 2.7955
Epoch 161/1000
7/7 [==============================] - 0s 26ms/step - loss: 2.3373 - mean_absolute_error: 1.1548 - val_loss: 13.0394 - val_mean_absolute_error: 2.7147
Epoch 162/1000
7/7 [==============================] - 0s 26ms/step - loss: 2.2312 - mean_absolute_error: 1.1169 - val_loss: 13.0918 - val_mean_absolute_error: 2.7516
Epoch 163/1000
7/7 [==============================] - 0s 23ms/step - loss: 2.4024 - mean_absolute_error: 1.1518 - val_loss: 13.1048 - val_mean_absolute_error: 2.7361
Epoch 164/1000
7/7 [==============================] - 0s 22ms/step - loss: 2.2814 - mean_absolute_error: 1.1466 - val_loss: 12.8048 - val_mean_absolute_error: 2.7271
Epoch 165/1000
7/7 [==============================] - 0s 23ms/step - loss: 2.3748 - mean_absolute_error: 1.1398 - val_loss: 14.5632 - val_mean_absolute_error: 2.7724
Epoch 166/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.4541 - mean_absolute_error: 1.1507 - val_loss: 13.0304 - val_mean_absolute_error: 2.6723
Epoch 167/1000
7/7 [==============================] - 0s 22ms/step - loss: 2.0612 - mean_absolute_error: 1.0723 - val_loss: 14.1075 - val_mean_absolute_error: 2.8420
Epoch 168/1000
7/7 [==============================] - 0s 23ms/step - loss: 2.4335 - mean_absolute_error: 1.1865 - val_loss: 12.8792 - val_mean_absolute_error: 2.6578
Epoch 169/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.1815 - mean_absolute_error: 1.1049 - val_loss: 15.4137 - val_mean_absolute_error: 2.9736
Epoch 170/1000
7/7 [==============================] - 0s 23ms/step - loss: 2.0418 - mean_absolute_error: 1.0472 - val_loss: 13.8005 - val_mean_absolute_error: 2.8009
Epoch 171/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9532 - mean_absolute_error: 0.9938 - val_loss: 14.0068 - val_mean_absolute_error: 2.8472
Epoch 172/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.9873 - mean_absolute_error: 1.0495 - val_loss: 12.3222 - val_mean_absolute_error: 2.6145
Epoch 173/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.9885 - mean_absolute_error: 1.0353 - val_loss: 13.7077 - val_mean_absolute_error: 2.7862
Epoch 174/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.8673 - mean_absolute_error: 0.9910 - val_loss: 13.6921 - val_mean_absolute_error: 2.7420
Epoch 175/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.1969 - mean_absolute_error: 1.0849 - val_loss: 13.3662 - val_mean_absolute_error: 2.7254
Epoch 176/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.8713 - mean_absolute_error: 1.0142 - val_loss: 15.2903 - val_mean_absolute_error: 2.9051
Epoch 177/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.0599 - mean_absolute_error: 1.0423 - val_loss: 12.9603 - val_mean_absolute_error: 2.6559
Epoch 178/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.1001 - mean_absolute_error: 1.0420 - val_loss: 13.5828 - val_mean_absolute_error: 2.8353
Epoch 179/1000
7/7 [==============================] - 0s 30ms/step - loss: 1.9582 - mean_absolute_error: 1.0317 - val_loss: 12.7807 - val_mean_absolute_error: 2.6364
Epoch 180/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.0338 - mean_absolute_error: 1.0638 - val_loss: 14.0145 - val_mean_absolute_error: 2.8171
Epoch 181/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8746 - mean_absolute_error: 0.9876 - val_loss: 13.6976 - val_mean_absolute_error: 2.8184
Epoch 182/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.7365 - mean_absolute_error: 0.9599 - val_loss: 14.4548 - val_mean_absolute_error: 2.9051
Epoch 183/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.7259 - mean_absolute_error: 0.9293 - val_loss: 14.2060 - val_mean_absolute_error: 2.8164
Epoch 184/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.9007 - mean_absolute_error: 0.9507 - val_loss: 13.6237 - val_mean_absolute_error: 2.7271
Epoch 185/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.9328 - mean_absolute_error: 0.9810 - val_loss: 15.0218 - val_mean_absolute_error: 2.9993
Epoch 186/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.2197 - mean_absolute_error: 1.0966 - val_loss: 13.3080 - val_mean_absolute_error: 2.6941
Epoch 187/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.1156 - mean_absolute_error: 1.0894 - val_loss: 13.9135 - val_mean_absolute_error: 2.7584
Epoch 188/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.2516 - mean_absolute_error: 1.0991 - val_loss: 13.2770 - val_mean_absolute_error: 2.7714
Epoch 189/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8079 - mean_absolute_error: 0.9854 - val_loss: 15.2468 - val_mean_absolute_error: 2.9587
Epoch 190/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8021 - mean_absolute_error: 0.9856 - val_loss: 13.5470 - val_mean_absolute_error: 2.7510
Epoch 191/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.6388 - mean_absolute_error: 0.9125 - val_loss: 13.7497 - val_mean_absolute_error: 2.8040
Epoch 192/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5547 - mean_absolute_error: 0.9015 - val_loss: 14.2507 - val_mean_absolute_error: 2.8663
Epoch 193/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.6243 - mean_absolute_error: 0.9020 - val_loss: 14.2628 - val_mean_absolute_error: 2.8185
Epoch 194/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.5147 - mean_absolute_error: 0.8592 - val_loss: 14.2280 - val_mean_absolute_error: 2.8011
Epoch 195/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.7417 - mean_absolute_error: 0.9261 - val_loss: 14.9307 - val_mean_absolute_error: 2.9519
Epoch 196/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.8947 - mean_absolute_error: 1.0164 - val_loss: 14.7871 - val_mean_absolute_error: 2.9151
Epoch 197/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9367 - mean_absolute_error: 1.0255 - val_loss: 13.8581 - val_mean_absolute_error: 2.7242
Epoch 198/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.6423 - mean_absolute_error: 0.9306 - val_loss: 14.8666 - val_mean_absolute_error: 3.0509
Epoch 199/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5193 - mean_absolute_error: 0.9141 - val_loss: 14.0924 - val_mean_absolute_error: 2.7342
Epoch 200/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.6421 - mean_absolute_error: 0.9297 - val_loss: 14.9141 - val_mean_absolute_error: 2.8639
Epoch 201/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.8521 - mean_absolute_error: 0.9863 - val_loss: 14.2642 - val_mean_absolute_error: 2.8467
Epoch 202/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9017 - mean_absolute_error: 1.0165 - val_loss: 13.1774 - val_mean_absolute_error: 2.7270
Epoch 203/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.1549 - mean_absolute_error: 1.0425 - val_loss: 14.9773 - val_mean_absolute_error: 2.9437
Epoch 204/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.5397 - mean_absolute_error: 0.9091 - val_loss: 13.9316 - val_mean_absolute_error: 2.8079
Epoch 205/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.6839 - mean_absolute_error: 0.9766 - val_loss: 14.4063 - val_mean_absolute_error: 2.9925
Epoch 206/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.6357 - mean_absolute_error: 0.9348 - val_loss: 14.0010 - val_mean_absolute_error: 2.8300
Epoch 207/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.5466 - mean_absolute_error: 0.8789 - val_loss: 14.2251 - val_mean_absolute_error: 2.7963
Epoch 208/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.6866 - mean_absolute_error: 0.9034 - val_loss: 13.8348 - val_mean_absolute_error: 2.8010
Epoch 209/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.4978 - mean_absolute_error: 0.8927 - val_loss: 14.7813 - val_mean_absolute_error: 2.9321
Epoch 210/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.5405 - mean_absolute_error: 0.9127 - val_loss: 14.3245 - val_mean_absolute_error: 2.7944
Epoch 211/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5005 - mean_absolute_error: 0.8884 - val_loss: 14.6576 - val_mean_absolute_error: 2.9000
Epoch 212/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.2763 - mean_absolute_error: 0.8172 - val_loss: 13.7831 - val_mean_absolute_error: 2.7710
Epoch 213/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.3272 - mean_absolute_error: 0.8402 - val_loss: 15.5701 - val_mean_absolute_error: 3.0109
Epoch 214/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.3822 - mean_absolute_error: 0.8589 - val_loss: 14.6657 - val_mean_absolute_error: 2.8942
Epoch 215/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.7019 - mean_absolute_error: 0.9370 - val_loss: 14.3298 - val_mean_absolute_error: 2.8113
Epoch 216/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.1503 - mean_absolute_error: 0.9328 - val_loss: 16.3933 - val_mean_absolute_error: 3.0976
Epoch 217/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.6521 - mean_absolute_error: 0.9415 - val_loss: 14.2364 - val_mean_absolute_error: 2.7802
Epoch 218/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.4702 - mean_absolute_error: 0.9206 - val_loss: 15.7740 - val_mean_absolute_error: 3.0242
Epoch 219/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.3940 - mean_absolute_error: 0.8803 - val_loss: 15.0103 - val_mean_absolute_error: 2.8447
Epoch 220/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.2756 - mean_absolute_error: 0.8146 - val_loss: 15.4107 - val_mean_absolute_error: 3.0069
Epoch 221/1000
7/7 [==============================] - 0s 25ms/step - loss: 1.3417 - mean_absolute_error: 0.8307 - val_loss: 14.2270 - val_mean_absolute_error: 2.8350
Epoch 222/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.1758 - mean_absolute_error: 0.7610 - val_loss: 15.7742 - val_mean_absolute_error: 2.9761
Epoch 223/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2007 - mean_absolute_error: 0.7830 - val_loss: 15.2184 - val_mean_absolute_error: 2.9057
Epoch 224/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2224 - mean_absolute_error: 0.7676 - val_loss: 14.4776 - val_mean_absolute_error: 2.8340
Epoch 225/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.4082 - mean_absolute_error: 0.8458 - val_loss: 14.4805 - val_mean_absolute_error: 2.8767
Epoch 226/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.2980 - mean_absolute_error: 0.8263 - val_loss: 15.7655 - val_mean_absolute_error: 3.0428
Epoch 227/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.6383 - mean_absolute_error: 0.9247 - val_loss: 14.4220 - val_mean_absolute_error: 2.7741
Epoch 228/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.5811 - mean_absolute_error: 0.9161 - val_loss: 15.5395 - val_mean_absolute_error: 3.0118
Epoch 229/1000
7/7 [==============================] - 0s 30ms/step - loss: 1.4880 - mean_absolute_error: 0.8699 - val_loss: 14.9694 - val_mean_absolute_error: 2.9395
Epoch 230/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.5611 - mean_absolute_error: 0.9404 - val_loss: 14.1237 - val_mean_absolute_error: 2.7715
Epoch 231/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.2579 - mean_absolute_error: 1.1156 - val_loss: 16.7146 - val_mean_absolute_error: 3.3250
Epoch 232/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.5740 - mean_absolute_error: 1.2576 - val_loss: 14.4687 - val_mean_absolute_error: 2.7551
Epoch 233/1000
7/7 [==============================] - 0s 25ms/step - loss: 3.8510 - mean_absolute_error: 1.3761 - val_loss: 15.4115 - val_mean_absolute_error: 2.9939
Epoch 234/1000
7/7 [==============================] - 0s 29ms/step - loss: 2.2850 - mean_absolute_error: 1.1216 - val_loss: 14.7552 - val_mean_absolute_error: 2.8406
Epoch 235/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.7677 - mean_absolute_error: 1.0060 - val_loss: 15.8288 - val_mean_absolute_error: 3.0458
Epoch 236/1000
7/7 [==============================] - 0s 24ms/step - loss: 1.5349 - mean_absolute_error: 0.9227 - val_loss: 13.6365 - val_mean_absolute_error: 2.7268
Epoch 237/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.3306 - mean_absolute_error: 0.8358 - val_loss: 15.3777 - val_mean_absolute_error: 2.9796
Epoch 238/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.3564 - mean_absolute_error: 0.8291 - val_loss: 14.0862 - val_mean_absolute_error: 2.8010
Epoch 239/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.1859 - mean_absolute_error: 0.7785 - val_loss: 13.9662 - val_mean_absolute_error: 2.8136
Epoch 240/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.1614 - mean_absolute_error: 0.7607 - val_loss: 14.0564 - val_mean_absolute_error: 2.7858
Epoch 241/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1536 - mean_absolute_error: 0.7767 - val_loss: 14.7293 - val_mean_absolute_error: 2.8781
Epoch 242/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1018 - mean_absolute_error: 0.7357 - val_loss: 14.9157 - val_mean_absolute_error: 2.9550
Epoch 243/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9745 - mean_absolute_error: 0.6784 - val_loss: 15.5461 - val_mean_absolute_error: 2.8745
Epoch 244/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9645 - mean_absolute_error: 0.6693 - val_loss: 15.0168 - val_mean_absolute_error: 2.9746
Epoch 245/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0143 - mean_absolute_error: 0.6795 - val_loss: 14.8649 - val_mean_absolute_error: 2.8693
Epoch 246/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0080 - mean_absolute_error: 0.6942 - val_loss: 14.6346 - val_mean_absolute_error: 2.7982
Epoch 247/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.0619 - mean_absolute_error: 0.7199 - val_loss: 15.1219 - val_mean_absolute_error: 2.9749
Epoch 248/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.2095 - mean_absolute_error: 0.7731 - val_loss: 14.1458 - val_mean_absolute_error: 2.8126
Epoch 249/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.1629 - mean_absolute_error: 0.7667 - val_loss: 15.4341 - val_mean_absolute_error: 2.9715
Epoch 250/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.2383 - mean_absolute_error: 0.8085 - val_loss: 14.2865 - val_mean_absolute_error: 2.8919
Epoch 251/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.2421 - mean_absolute_error: 0.8277 - val_loss: 15.3616 - val_mean_absolute_error: 2.9923
Epoch 252/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1956 - mean_absolute_error: 0.7607 - val_loss: 14.7350 - val_mean_absolute_error: 2.8229
Epoch 253/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1231 - mean_absolute_error: 0.7367 - val_loss: 14.1532 - val_mean_absolute_error: 2.8366
Epoch 254/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9324 - mean_absolute_error: 0.6504 - val_loss: 14.6484 - val_mean_absolute_error: 2.8747
Epoch 255/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0646 - mean_absolute_error: 0.7093 - val_loss: 14.9079 - val_mean_absolute_error: 2.8950
Epoch 256/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8943 - mean_absolute_error: 0.6425 - val_loss: 14.6101 - val_mean_absolute_error: 2.8533
Epoch 257/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9035 - mean_absolute_error: 0.6422 - val_loss: 14.8931 - val_mean_absolute_error: 2.8588
Epoch 258/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9626 - mean_absolute_error: 0.6650 - val_loss: 14.6791 - val_mean_absolute_error: 2.8662
Epoch 259/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0232 - mean_absolute_error: 0.7010 - val_loss: 15.0942 - val_mean_absolute_error: 2.8759
Epoch 260/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0783 - mean_absolute_error: 0.7030 - val_loss: 14.0869 - val_mean_absolute_error: 2.8905
Epoch 261/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9616 - mean_absolute_error: 0.6819 - val_loss: 14.8983 - val_mean_absolute_error: 2.9047
Epoch 262/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9837 - mean_absolute_error: 0.6881 - val_loss: 15.5244 - val_mean_absolute_error: 3.0657
Epoch 263/1000
7/7 [==============================] - 0s 26ms/step - loss: 1.2888 - mean_absolute_error: 0.8004 - val_loss: 13.7884 - val_mean_absolute_error: 2.8221
Epoch 264/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.2546 - mean_absolute_error: 0.7493 - val_loss: 14.6765 - val_mean_absolute_error: 3.0004
Epoch 265/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0026 - mean_absolute_error: 0.7151 - val_loss: 14.3838 - val_mean_absolute_error: 2.8242
Epoch 266/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.9443 - mean_absolute_error: 0.6796 - val_loss: 15.6352 - val_mean_absolute_error: 3.1169
Epoch 267/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.9576 - mean_absolute_error: 0.7224 - val_loss: 13.5848 - val_mean_absolute_error: 2.7225
Epoch 268/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.9882 - mean_absolute_error: 0.6677 - val_loss: 14.7937 - val_mean_absolute_error: 2.9037
Epoch 269/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9179 - mean_absolute_error: 0.6338 - val_loss: 14.8672 - val_mean_absolute_error: 2.9118
Epoch 270/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8260 - mean_absolute_error: 0.6211 - val_loss: 13.7695 - val_mean_absolute_error: 2.7538
Epoch 271/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1958 - mean_absolute_error: 0.6820 - val_loss: 15.4077 - val_mean_absolute_error: 2.9772
Epoch 272/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.6269 - mean_absolute_error: 0.7616 - val_loss: 14.9109 - val_mean_absolute_error: 2.8642
Epoch 273/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.0528 - mean_absolute_error: 0.7576 - val_loss: 15.1503 - val_mean_absolute_error: 2.9716
Epoch 274/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1252 - mean_absolute_error: 0.7180 - val_loss: 14.3404 - val_mean_absolute_error: 2.8342
Epoch 275/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9894 - mean_absolute_error: 0.6830 - val_loss: 15.5529 - val_mean_absolute_error: 3.0350
Epoch 276/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9125 - mean_absolute_error: 0.6426 - val_loss: 14.8019 - val_mean_absolute_error: 2.8413
Epoch 277/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8621 - mean_absolute_error: 0.6476 - val_loss: 14.4121 - val_mean_absolute_error: 2.8434
Epoch 278/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8364 - mean_absolute_error: 0.6459 - val_loss: 14.7961 - val_mean_absolute_error: 2.9094
Epoch 279/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.8193 - mean_absolute_error: 0.6404 - val_loss: 14.4032 - val_mean_absolute_error: 2.8262
Epoch 280/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0442 - mean_absolute_error: 0.7197 - val_loss: 14.6968 - val_mean_absolute_error: 2.7982
Epoch 281/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9785 - mean_absolute_error: 0.6976 - val_loss: 15.1016 - val_mean_absolute_error: 3.0245
Epoch 282/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0210 - mean_absolute_error: 0.7094 - val_loss: 14.8584 - val_mean_absolute_error: 2.9468
Epoch 283/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8566 - mean_absolute_error: 0.6541 - val_loss: 14.0730 - val_mean_absolute_error: 2.7784
Epoch 284/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.7958 - mean_absolute_error: 0.6235 - val_loss: 14.8787 - val_mean_absolute_error: 2.9511
Epoch 285/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0381 - mean_absolute_error: 0.6915 - val_loss: 14.5259 - val_mean_absolute_error: 2.8605
Epoch 286/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.3503 - mean_absolute_error: 0.7670 - val_loss: 15.2049 - val_mean_absolute_error: 2.9682
Epoch 287/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8944 - mean_absolute_error: 0.6985 - val_loss: 13.6927 - val_mean_absolute_error: 2.8336
Epoch 288/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8793 - mean_absolute_error: 0.6504 - val_loss: 14.9116 - val_mean_absolute_error: 3.0028
Epoch 289/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0046 - mean_absolute_error: 0.6926 - val_loss: 15.3686 - val_mean_absolute_error: 2.9122
Epoch 290/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8954 - mean_absolute_error: 0.6464 - val_loss: 14.0229 - val_mean_absolute_error: 2.8282
Epoch 291/1000
7/7 [==============================] - 0s 35ms/step - loss: 1.0916 - mean_absolute_error: 0.6758 - val_loss: 14.8383 - val_mean_absolute_error: 2.9217
Epoch 292/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.9535 - mean_absolute_error: 0.6681 - val_loss: 13.8383 - val_mean_absolute_error: 2.8656
Epoch 293/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8694 - mean_absolute_error: 0.6223 - val_loss: 13.9622 - val_mean_absolute_error: 2.8714
Epoch 294/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7727 - mean_absolute_error: 0.5858 - val_loss: 15.1241 - val_mean_absolute_error: 2.9218
Epoch 295/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7843 - mean_absolute_error: 0.5716 - val_loss: 13.9671 - val_mean_absolute_error: 2.8031
Epoch 296/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7250 - mean_absolute_error: 0.5623 - val_loss: 14.3183 - val_mean_absolute_error: 2.9810
Epoch 297/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6994 - mean_absolute_error: 0.5580 - val_loss: 14.2512 - val_mean_absolute_error: 2.7489
Epoch 298/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7791 - mean_absolute_error: 0.5980 - val_loss: 14.4619 - val_mean_absolute_error: 3.0089
Epoch 299/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7861 - mean_absolute_error: 0.6093 - val_loss: 14.2137 - val_mean_absolute_error: 2.8643
Epoch 300/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.6893 - mean_absolute_error: 0.5760 - val_loss: 14.4391 - val_mean_absolute_error: 2.8727
Epoch 301/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6561 - mean_absolute_error: 0.5337 - val_loss: 14.5410 - val_mean_absolute_error: 2.9610
Epoch 302/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6926 - mean_absolute_error: 0.5603 - val_loss: 13.9194 - val_mean_absolute_error: 2.8174
Epoch 303/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6357 - mean_absolute_error: 0.5364 - val_loss: 14.4482 - val_mean_absolute_error: 2.9114
Epoch 304/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6600 - mean_absolute_error: 0.5458 - val_loss: 14.3765 - val_mean_absolute_error: 2.8428
Epoch 305/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7172 - mean_absolute_error: 0.5743 - val_loss: 15.3226 - val_mean_absolute_error: 2.9731
Epoch 306/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7737 - mean_absolute_error: 0.6136 - val_loss: 14.2748 - val_mean_absolute_error: 2.8491
Epoch 307/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8235 - mean_absolute_error: 0.6262 - val_loss: 14.1584 - val_mean_absolute_error: 2.7963
Epoch 308/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8300 - mean_absolute_error: 0.6271 - val_loss: 15.0316 - val_mean_absolute_error: 3.0267
Epoch 309/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6591 - mean_absolute_error: 0.5414 - val_loss: 14.2179 - val_mean_absolute_error: 2.8809
Epoch 310/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7143 - mean_absolute_error: 0.5680 - val_loss: 13.4670 - val_mean_absolute_error: 2.7884
Epoch 311/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6494 - mean_absolute_error: 0.5607 - val_loss: 15.2140 - val_mean_absolute_error: 2.9945
Epoch 312/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0001 - mean_absolute_error: 0.6376 - val_loss: 14.2290 - val_mean_absolute_error: 2.7742
Epoch 313/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0495 - mean_absolute_error: 0.6808 - val_loss: 13.2752 - val_mean_absolute_error: 2.9306
Epoch 314/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8175 - mean_absolute_error: 0.6267 - val_loss: 14.4751 - val_mean_absolute_error: 2.8879
Epoch 315/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.3225 - mean_absolute_error: 0.7680 - val_loss: 14.7107 - val_mean_absolute_error: 2.8287
Epoch 316/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8211 - mean_absolute_error: 0.6542 - val_loss: 13.6500 - val_mean_absolute_error: 2.8660
Epoch 317/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8346 - mean_absolute_error: 0.6348 - val_loss: 13.8961 - val_mean_absolute_error: 2.8832
Epoch 318/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8098 - mean_absolute_error: 0.6288 - val_loss: 15.0272 - val_mean_absolute_error: 2.8902
Epoch 319/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7009 - mean_absolute_error: 0.5890 - val_loss: 13.8675 - val_mean_absolute_error: 2.8434
Epoch 320/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6661 - mean_absolute_error: 0.5453 - val_loss: 14.2193 - val_mean_absolute_error: 2.8618
Epoch 321/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6166 - mean_absolute_error: 0.5355 - val_loss: 13.5175 - val_mean_absolute_error: 2.7696
Epoch 322/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7430 - mean_absolute_error: 0.5960 - val_loss: 14.4607 - val_mean_absolute_error: 2.9581
Epoch 323/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7392 - mean_absolute_error: 0.6133 - val_loss: 13.7395 - val_mean_absolute_error: 2.7658
Epoch 324/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7276 - mean_absolute_error: 0.5715 - val_loss: 14.9507 - val_mean_absolute_error: 3.0139
Epoch 325/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1875 - mean_absolute_error: 0.7549 - val_loss: 13.9561 - val_mean_absolute_error: 2.7930
Epoch 326/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2626 - mean_absolute_error: 0.8518 - val_loss: 15.1441 - val_mean_absolute_error: 3.0035
Epoch 327/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4699 - mean_absolute_error: 0.8510 - val_loss: 13.8350 - val_mean_absolute_error: 2.8456
Epoch 328/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.0256 - mean_absolute_error: 0.8333 - val_loss: 12.7075 - val_mean_absolute_error: 2.6183
Epoch 329/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.3759 - mean_absolute_error: 0.7640 - val_loss: 13.7991 - val_mean_absolute_error: 2.8305
Epoch 330/1000
7/7 [==============================] - 0s 17ms/step - loss: 1.0591 - mean_absolute_error: 0.7230 - val_loss: 13.9768 - val_mean_absolute_error: 2.8674
Epoch 331/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.9191 - mean_absolute_error: 0.6716 - val_loss: 13.4606 - val_mean_absolute_error: 2.7244
Epoch 332/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0174 - mean_absolute_error: 0.6963 - val_loss: 15.4180 - val_mean_absolute_error: 3.0912
Epoch 333/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8865 - mean_absolute_error: 0.6713 - val_loss: 13.9525 - val_mean_absolute_error: 2.8219
Epoch 334/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8465 - mean_absolute_error: 0.6283 - val_loss: 13.8559 - val_mean_absolute_error: 2.9138
Epoch 335/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6963 - mean_absolute_error: 0.5739 - val_loss: 14.5172 - val_mean_absolute_error: 2.9263
Epoch 336/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6934 - mean_absolute_error: 0.5434 - val_loss: 13.8758 - val_mean_absolute_error: 2.8171
Epoch 337/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8056 - mean_absolute_error: 0.5816 - val_loss: 14.8534 - val_mean_absolute_error: 2.9148
Epoch 338/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9246 - mean_absolute_error: 0.6810 - val_loss: 13.8262 - val_mean_absolute_error: 2.8329
Epoch 339/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1540 - mean_absolute_error: 0.6623 - val_loss: 14.1131 - val_mean_absolute_error: 2.8892
Epoch 340/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8899 - mean_absolute_error: 0.6227 - val_loss: 14.3756 - val_mean_absolute_error: 2.8925
Epoch 341/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7530 - mean_absolute_error: 0.5742 - val_loss: 14.3370 - val_mean_absolute_error: 2.8980
Epoch 342/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5845 - mean_absolute_error: 0.5024 - val_loss: 14.0896 - val_mean_absolute_error: 2.9056
Epoch 343/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4595 - mean_absolute_error: 0.4649 - val_loss: 13.6928 - val_mean_absolute_error: 2.7660
Epoch 344/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5516 - mean_absolute_error: 0.4920 - val_loss: 14.5258 - val_mean_absolute_error: 2.8632
Epoch 345/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5675 - mean_absolute_error: 0.5298 - val_loss: 15.3427 - val_mean_absolute_error: 3.0418
Epoch 346/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6827 - mean_absolute_error: 0.6121 - val_loss: 13.3984 - val_mean_absolute_error: 2.6906
Epoch 347/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6696 - mean_absolute_error: 0.5754 - val_loss: 15.4782 - val_mean_absolute_error: 3.0774
Epoch 348/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5841 - mean_absolute_error: 0.5148 - val_loss: 14.4647 - val_mean_absolute_error: 2.8107
Epoch 349/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5947 - mean_absolute_error: 0.5183 - val_loss: 13.9929 - val_mean_absolute_error: 2.8311
Epoch 350/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5067 - mean_absolute_error: 0.4745 - val_loss: 14.2053 - val_mean_absolute_error: 2.9430
Epoch 351/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5622 - mean_absolute_error: 0.4838 - val_loss: 14.7118 - val_mean_absolute_error: 2.8573
Epoch 352/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5515 - mean_absolute_error: 0.5255 - val_loss: 14.1842 - val_mean_absolute_error: 2.9134
Epoch 353/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5223 - mean_absolute_error: 0.5017 - val_loss: 14.7925 - val_mean_absolute_error: 2.9353
Epoch 354/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5779 - mean_absolute_error: 0.5425 - val_loss: 13.9457 - val_mean_absolute_error: 2.8297
Epoch 355/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5620 - mean_absolute_error: 0.5253 - val_loss: 14.2021 - val_mean_absolute_error: 2.8060
Epoch 356/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5203 - mean_absolute_error: 0.4996 - val_loss: 14.2668 - val_mean_absolute_error: 2.9188
Epoch 357/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4797 - mean_absolute_error: 0.4591 - val_loss: 13.8774 - val_mean_absolute_error: 2.8155
Epoch 358/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4502 - mean_absolute_error: 0.4704 - val_loss: 13.9423 - val_mean_absolute_error: 2.7980
Epoch 359/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5024 - mean_absolute_error: 0.4525 - val_loss: 13.8372 - val_mean_absolute_error: 2.8386
Epoch 360/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4193 - mean_absolute_error: 0.4160 - val_loss: 14.8512 - val_mean_absolute_error: 2.9842
Epoch 361/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4879 - mean_absolute_error: 0.4726 - val_loss: 13.5405 - val_mean_absolute_error: 2.8023
Epoch 362/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4405 - mean_absolute_error: 0.4496 - val_loss: 13.1217 - val_mean_absolute_error: 2.6877
Epoch 363/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4909 - mean_absolute_error: 0.5243 - val_loss: 15.4354 - val_mean_absolute_error: 3.1275
Epoch 364/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.7021 - mean_absolute_error: 0.6102 - val_loss: 14.2164 - val_mean_absolute_error: 2.8535
Epoch 365/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4336 - mean_absolute_error: 0.4718 - val_loss: 13.9973 - val_mean_absolute_error: 2.8131
Epoch 366/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3985 - mean_absolute_error: 0.4484 - val_loss: 14.9832 - val_mean_absolute_error: 3.0101
Epoch 367/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4042 - mean_absolute_error: 0.4362 - val_loss: 13.5860 - val_mean_absolute_error: 2.7392
Epoch 368/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6578 - mean_absolute_error: 0.5044 - val_loss: 14.4004 - val_mean_absolute_error: 2.9444
Epoch 369/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5473 - mean_absolute_error: 0.4811 - val_loss: 15.0652 - val_mean_absolute_error: 2.9398
Epoch 370/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6271 - mean_absolute_error: 0.5090 - val_loss: 12.9193 - val_mean_absolute_error: 2.7545
Epoch 371/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6057 - mean_absolute_error: 0.5713 - val_loss: 14.8020 - val_mean_absolute_error: 2.9458
Epoch 372/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5893 - mean_absolute_error: 0.5567 - val_loss: 14.1247 - val_mean_absolute_error: 2.8082
Epoch 373/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4541 - mean_absolute_error: 0.4768 - val_loss: 13.8466 - val_mean_absolute_error: 2.8314
Epoch 374/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4464 - mean_absolute_error: 0.4487 - val_loss: 13.4042 - val_mean_absolute_error: 2.8019
Epoch 375/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4280 - mean_absolute_error: 0.4422 - val_loss: 13.9582 - val_mean_absolute_error: 2.8649
Epoch 376/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3902 - mean_absolute_error: 0.4365 - val_loss: 13.9530 - val_mean_absolute_error: 2.8392
Epoch 377/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.4562 - mean_absolute_error: 0.4306 - val_loss: 13.6028 - val_mean_absolute_error: 2.8242
Epoch 378/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4664 - mean_absolute_error: 0.4565 - val_loss: 14.9062 - val_mean_absolute_error: 2.9799
Epoch 379/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.4533 - mean_absolute_error: 0.4719 - val_loss: 13.8565 - val_mean_absolute_error: 2.8127
Epoch 380/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.4554 - mean_absolute_error: 0.4641 - val_loss: 13.9057 - val_mean_absolute_error: 2.8217
Epoch 381/1000
7/7 [==============================] - 0s 37ms/step - loss: 0.4783 - mean_absolute_error: 0.4774 - val_loss: 14.4116 - val_mean_absolute_error: 2.9013
Epoch 382/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.5298 - mean_absolute_error: 0.4625 - val_loss: 13.8276 - val_mean_absolute_error: 2.7782
Epoch 383/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.5947 - mean_absolute_error: 0.4633 - val_loss: 15.0547 - val_mean_absolute_error: 3.1129
Epoch 384/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5894 - mean_absolute_error: 0.5010 - val_loss: 14.1438 - val_mean_absolute_error: 2.7943
Epoch 385/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6262 - mean_absolute_error: 0.5553 - val_loss: 13.9962 - val_mean_absolute_error: 2.7794
Epoch 386/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6834 - mean_absolute_error: 0.5769 - val_loss: 14.8004 - val_mean_absolute_error: 2.9307
Epoch 387/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7117 - mean_absolute_error: 0.5997 - val_loss: 15.2666 - val_mean_absolute_error: 2.9156
Epoch 388/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6189 - mean_absolute_error: 0.5978 - val_loss: 15.0259 - val_mean_absolute_error: 2.9536
Epoch 389/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7670 - mean_absolute_error: 0.6159 - val_loss: 13.5652 - val_mean_absolute_error: 2.7910
Epoch 390/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6400 - mean_absolute_error: 0.6199 - val_loss: 15.2481 - val_mean_absolute_error: 3.0441
Epoch 391/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5914 - mean_absolute_error: 0.6066 - val_loss: 14.1801 - val_mean_absolute_error: 3.0144
Epoch 392/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6175 - mean_absolute_error: 0.5293 - val_loss: 14.2531 - val_mean_absolute_error: 2.9052
Epoch 393/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4620 - mean_absolute_error: 0.4856 - val_loss: 14.7249 - val_mean_absolute_error: 2.9266
Epoch 394/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5434 - mean_absolute_error: 0.4659 - val_loss: 13.6665 - val_mean_absolute_error: 2.9400
Epoch 395/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0678 - mean_absolute_error: 0.5315 - val_loss: 13.1837 - val_mean_absolute_error: 2.7414
Epoch 396/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5992 - mean_absolute_error: 0.5039 - val_loss: 14.4124 - val_mean_absolute_error: 2.8134
Epoch 397/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5837 - mean_absolute_error: 0.4720 - val_loss: 14.4903 - val_mean_absolute_error: 2.9060
Epoch 398/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5538 - mean_absolute_error: 0.4912 - val_loss: 14.1971 - val_mean_absolute_error: 2.8836
Epoch 399/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7206 - mean_absolute_error: 0.5969 - val_loss: 14.5632 - val_mean_absolute_error: 2.9084
Epoch 400/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.7452 - mean_absolute_error: 0.6178 - val_loss: 13.0755 - val_mean_absolute_error: 2.8222
Epoch 401/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8869 - mean_absolute_error: 0.6185 - val_loss: 14.0143 - val_mean_absolute_error: 2.8313
Epoch 402/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5624 - mean_absolute_error: 0.5249 - val_loss: 14.2398 - val_mean_absolute_error: 2.9876
Epoch 403/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.6037 - mean_absolute_error: 0.5750 - val_loss: 13.9209 - val_mean_absolute_error: 2.8381
Epoch 404/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5616 - mean_absolute_error: 0.5415 - val_loss: 13.8407 - val_mean_absolute_error: 2.9255
Epoch 405/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5451 - mean_absolute_error: 0.5556 - val_loss: 14.2401 - val_mean_absolute_error: 2.8193
Epoch 406/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4820 - mean_absolute_error: 0.4960 - val_loss: 13.7601 - val_mean_absolute_error: 2.9317
Epoch 407/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5015 - mean_absolute_error: 0.4420 - val_loss: 14.5032 - val_mean_absolute_error: 3.0502
Epoch 408/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4607 - mean_absolute_error: 0.4567 - val_loss: 13.6502 - val_mean_absolute_error: 2.7737
Epoch 409/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3785 - mean_absolute_error: 0.4185 - val_loss: 13.9544 - val_mean_absolute_error: 2.8786
Epoch 410/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3941 - mean_absolute_error: 0.4190 - val_loss: 14.1925 - val_mean_absolute_error: 2.9114
Epoch 411/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3670 - mean_absolute_error: 0.4035 - val_loss: 13.5518 - val_mean_absolute_error: 2.7303
Epoch 412/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3319 - mean_absolute_error: 0.3618 - val_loss: 13.7443 - val_mean_absolute_error: 2.8821
Epoch 413/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.3272 - mean_absolute_error: 0.3910 - val_loss: 13.6265 - val_mean_absolute_error: 2.7471
Epoch 414/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2661 - mean_absolute_error: 0.3425 - val_loss: 12.9470 - val_mean_absolute_error: 2.7007
Epoch 415/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2878 - mean_absolute_error: 0.3556 - val_loss: 14.6028 - val_mean_absolute_error: 2.9881
Epoch 416/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3063 - mean_absolute_error: 0.3658 - val_loss: 13.5431 - val_mean_absolute_error: 2.8467
Epoch 417/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2911 - mean_absolute_error: 0.3452 - val_loss: 14.4358 - val_mean_absolute_error: 2.9185
Epoch 418/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3333 - mean_absolute_error: 0.3641 - val_loss: 13.2179 - val_mean_absolute_error: 2.7792
Epoch 419/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2790 - mean_absolute_error: 0.3677 - val_loss: 13.3728 - val_mean_absolute_error: 2.7860
Epoch 420/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2430 - mean_absolute_error: 0.3373 - val_loss: 14.3271 - val_mean_absolute_error: 2.9191
Epoch 421/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2646 - mean_absolute_error: 0.3459 - val_loss: 13.1163 - val_mean_absolute_error: 2.7634
Epoch 422/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3635 - mean_absolute_error: 0.3740 - val_loss: 13.5994 - val_mean_absolute_error: 2.8216
Epoch 423/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1488 - mean_absolute_error: 0.5540 - val_loss: 14.0456 - val_mean_absolute_error: 2.8183
Epoch 424/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7083 - mean_absolute_error: 0.5489 - val_loss: 12.3500 - val_mean_absolute_error: 2.7339
Epoch 425/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7859 - mean_absolute_error: 0.5303 - val_loss: 14.0167 - val_mean_absolute_error: 2.8275
Epoch 426/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7110 - mean_absolute_error: 0.5652 - val_loss: 13.7333 - val_mean_absolute_error: 2.8561
Epoch 427/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4642 - mean_absolute_error: 0.5051 - val_loss: 13.2311 - val_mean_absolute_error: 2.7714
Epoch 428/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4186 - mean_absolute_error: 0.4744 - val_loss: 12.6010 - val_mean_absolute_error: 2.6881
Epoch 429/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4804 - mean_absolute_error: 0.4789 - val_loss: 13.9591 - val_mean_absolute_error: 2.8846
Epoch 430/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3727 - mean_absolute_error: 0.4315 - val_loss: 13.0936 - val_mean_absolute_error: 2.7942
Epoch 431/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.3012 - mean_absolute_error: 0.3906 - val_loss: 13.1466 - val_mean_absolute_error: 2.7782
Epoch 432/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3104 - mean_absolute_error: 0.3616 - val_loss: 13.0090 - val_mean_absolute_error: 2.7647
Epoch 433/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3312 - mean_absolute_error: 0.3762 - val_loss: 13.4493 - val_mean_absolute_error: 2.8733
Epoch 434/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.5373 - mean_absolute_error: 0.4118 - val_loss: 13.4472 - val_mean_absolute_error: 2.8477
Epoch 435/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4227 - mean_absolute_error: 0.3848 - val_loss: 14.4874 - val_mean_absolute_error: 2.9819
Epoch 436/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4148 - mean_absolute_error: 0.4069 - val_loss: 14.7439 - val_mean_absolute_error: 3.0063
Epoch 437/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5458 - mean_absolute_error: 0.4976 - val_loss: 13.8047 - val_mean_absolute_error: 2.8910
Epoch 438/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.4014 - mean_absolute_error: 0.4233 - val_loss: 13.5312 - val_mean_absolute_error: 2.8067
Epoch 439/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5031 - mean_absolute_error: 0.4869 - val_loss: 14.1119 - val_mean_absolute_error: 2.9569
Epoch 440/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4046 - mean_absolute_error: 0.4101 - val_loss: 14.2625 - val_mean_absolute_error: 2.8925
Epoch 441/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4145 - mean_absolute_error: 0.4263 - val_loss: 13.5904 - val_mean_absolute_error: 2.9163
Epoch 442/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4678 - mean_absolute_error: 0.4958 - val_loss: 14.7541 - val_mean_absolute_error: 3.0457
Epoch 443/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5844 - mean_absolute_error: 0.4777 - val_loss: 13.1424 - val_mean_absolute_error: 2.8373
Epoch 444/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4749 - mean_absolute_error: 0.4533 - val_loss: 13.8761 - val_mean_absolute_error: 2.9936
Epoch 445/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3960 - mean_absolute_error: 0.3684 - val_loss: 13.8070 - val_mean_absolute_error: 2.9845
Epoch 446/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.4010 - mean_absolute_error: 0.3959 - val_loss: 14.1135 - val_mean_absolute_error: 2.9467
Epoch 447/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3323 - mean_absolute_error: 0.3387 - val_loss: 13.7232 - val_mean_absolute_error: 2.9043
Epoch 448/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3072 - mean_absolute_error: 0.3207 - val_loss: 13.8845 - val_mean_absolute_error: 2.9155
Epoch 449/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2985 - mean_absolute_error: 0.2973 - val_loss: 14.0103 - val_mean_absolute_error: 2.9276
Epoch 450/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2990 - mean_absolute_error: 0.3012 - val_loss: 14.2808 - val_mean_absolute_error: 3.0260
Epoch 451/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3138 - mean_absolute_error: 0.2885 - val_loss: 13.5403 - val_mean_absolute_error: 2.9229
Epoch 452/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.3289 - mean_absolute_error: 0.3041 - val_loss: 13.9211 - val_mean_absolute_error: 2.9321
Epoch 453/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.9625 - mean_absolute_error: 0.4619 - val_loss: 13.9263 - val_mean_absolute_error: 3.0322
Epoch 454/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.1198 - mean_absolute_error: 0.6691 - val_loss: 13.7401 - val_mean_absolute_error: 2.8305
Epoch 455/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0061 - mean_absolute_error: 0.6357 - val_loss: 13.5849 - val_mean_absolute_error: 2.8604
Epoch 456/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9038 - mean_absolute_error: 0.5877 - val_loss: 13.9312 - val_mean_absolute_error: 2.9396
Epoch 457/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7801 - mean_absolute_error: 0.5672 - val_loss: 13.4106 - val_mean_absolute_error: 2.8520
Epoch 458/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9256 - mean_absolute_error: 0.5766 - val_loss: 14.4511 - val_mean_absolute_error: 3.0389
Epoch 459/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5129 - mean_absolute_error: 0.6662 - val_loss: 13.5682 - val_mean_absolute_error: 2.8899
Epoch 460/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5448 - mean_absolute_error: 0.6652 - val_loss: 13.3512 - val_mean_absolute_error: 2.7714
Epoch 461/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.4427 - mean_absolute_error: 0.7378 - val_loss: 15.1325 - val_mean_absolute_error: 3.0471
Epoch 462/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.4148 - mean_absolute_error: 0.8986 - val_loss: 14.1315 - val_mean_absolute_error: 2.7851
Epoch 463/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.3699 - mean_absolute_error: 0.7764 - val_loss: 13.8955 - val_mean_absolute_error: 3.0007
Epoch 464/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.1255 - mean_absolute_error: 0.6788 - val_loss: 13.6991 - val_mean_absolute_error: 2.9719
Epoch 465/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0048 - mean_absolute_error: 0.6606 - val_loss: 13.4004 - val_mean_absolute_error: 2.7704
Epoch 466/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0692 - mean_absolute_error: 0.6740 - val_loss: 12.8422 - val_mean_absolute_error: 2.7991
Epoch 467/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.2775 - mean_absolute_error: 0.6779 - val_loss: 13.5324 - val_mean_absolute_error: 2.7083
Epoch 468/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.4483 - mean_absolute_error: 0.6742 - val_loss: 13.4707 - val_mean_absolute_error: 2.7837
Epoch 469/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2464 - mean_absolute_error: 0.6525 - val_loss: 13.9963 - val_mean_absolute_error: 2.8792
Epoch 470/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0505 - mean_absolute_error: 0.6492 - val_loss: 13.6430 - val_mean_absolute_error: 2.7537
Epoch 471/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7727 - mean_absolute_error: 0.5023 - val_loss: 13.6524 - val_mean_absolute_error: 2.9402
Epoch 472/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8393 - mean_absolute_error: 0.5149 - val_loss: 13.6786 - val_mean_absolute_error: 2.9190
Epoch 473/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.6637 - mean_absolute_error: 0.4600 - val_loss: 13.8980 - val_mean_absolute_error: 2.8058
Epoch 474/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.6534 - mean_absolute_error: 0.4619 - val_loss: 13.1283 - val_mean_absolute_error: 2.8004
Epoch 475/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.7250 - mean_absolute_error: 0.5022 - val_loss: 13.3989 - val_mean_absolute_error: 2.8392
Epoch 476/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.6747 - mean_absolute_error: 0.4348 - val_loss: 13.4179 - val_mean_absolute_error: 2.8171
Epoch 477/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.8883 - mean_absolute_error: 0.5171 - val_loss: 13.1078 - val_mean_absolute_error: 2.8162
Epoch 478/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.7234 - mean_absolute_error: 0.4810 - val_loss: 12.6723 - val_mean_absolute_error: 2.7590
Epoch 479/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.6337 - mean_absolute_error: 0.4518 - val_loss: 13.9750 - val_mean_absolute_error: 2.8389
Epoch 480/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5588 - mean_absolute_error: 0.4518 - val_loss: 13.6585 - val_mean_absolute_error: 2.8787
Epoch 481/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6642 - mean_absolute_error: 0.4668 - val_loss: 14.5275 - val_mean_absolute_error: 3.0041
Epoch 482/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9953 - mean_absolute_error: 0.5912 - val_loss: 14.6007 - val_mean_absolute_error: 2.8212
Epoch 483/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.7996 - mean_absolute_error: 0.6318 - val_loss: 12.7941 - val_mean_absolute_error: 2.7623
Epoch 484/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.8197 - mean_absolute_error: 0.6204 - val_loss: 15.1212 - val_mean_absolute_error: 3.0780
Epoch 485/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.7885 - mean_absolute_error: 0.5810 - val_loss: 14.0064 - val_mean_absolute_error: 2.8798
Epoch 486/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5289 - mean_absolute_error: 0.4575 - val_loss: 13.2925 - val_mean_absolute_error: 2.8543
Epoch 487/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.6550 - mean_absolute_error: 0.4870 - val_loss: 12.9255 - val_mean_absolute_error: 2.8578
Epoch 488/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5139 - mean_absolute_error: 0.4094 - val_loss: 13.4765 - val_mean_absolute_error: 2.8459
Epoch 489/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4060 - mean_absolute_error: 0.3640 - val_loss: 12.8902 - val_mean_absolute_error: 2.7824
Epoch 490/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4335 - mean_absolute_error: 0.3990 - val_loss: 13.5204 - val_mean_absolute_error: 2.8949
Epoch 491/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4396 - mean_absolute_error: 0.3688 - val_loss: 13.2686 - val_mean_absolute_error: 2.8326
Epoch 492/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5094 - mean_absolute_error: 0.3887 - val_loss: 13.0784 - val_mean_absolute_error: 2.7847
Epoch 493/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4684 - mean_absolute_error: 0.3709 - val_loss: 13.6174 - val_mean_absolute_error: 2.8816
Epoch 494/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4262 - mean_absolute_error: 0.3972 - val_loss: 13.7537 - val_mean_absolute_error: 2.9284
Epoch 495/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4013 - mean_absolute_error: 0.3646 - val_loss: 12.9363 - val_mean_absolute_error: 2.7456
Epoch 496/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4150 - mean_absolute_error: 0.3992 - val_loss: 13.9029 - val_mean_absolute_error: 2.9410
Epoch 497/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3313 - mean_absolute_error: 0.3808 - val_loss: 13.4273 - val_mean_absolute_error: 2.8710
Epoch 498/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3063 - mean_absolute_error: 0.3330 - val_loss: 13.2896 - val_mean_absolute_error: 2.8436
Epoch 499/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2799 - mean_absolute_error: 0.3309 - val_loss: 13.9772 - val_mean_absolute_error: 2.9364
Epoch 500/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2855 - mean_absolute_error: 0.3196 - val_loss: 13.1030 - val_mean_absolute_error: 2.7856
Epoch 501/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2725 - mean_absolute_error: 0.3164 - val_loss: 14.0188 - val_mean_absolute_error: 2.9430
Epoch 502/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4399 - mean_absolute_error: 0.3466 - val_loss: 14.0528 - val_mean_absolute_error: 2.9083
Epoch 503/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.3846 - mean_absolute_error: 0.3737 - val_loss: 13.3117 - val_mean_absolute_error: 2.7880
Epoch 504/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2916 - mean_absolute_error: 0.3360 - val_loss: 13.8255 - val_mean_absolute_error: 2.9138
Epoch 505/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3098 - mean_absolute_error: 0.3563 - val_loss: 13.8587 - val_mean_absolute_error: 2.8655
Epoch 506/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2686 - mean_absolute_error: 0.3387 - val_loss: 13.0770 - val_mean_absolute_error: 2.8134
Epoch 507/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2280 - mean_absolute_error: 0.2980 - val_loss: 13.3853 - val_mean_absolute_error: 2.8154
Epoch 508/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2466 - mean_absolute_error: 0.3159 - val_loss: 13.8036 - val_mean_absolute_error: 2.9019
Epoch 509/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.3174 - mean_absolute_error: 0.3172 - val_loss: 13.3536 - val_mean_absolute_error: 2.7987
Epoch 510/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2007 - mean_absolute_error: 0.2889 - val_loss: 13.5399 - val_mean_absolute_error: 2.8462
Epoch 511/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2230 - mean_absolute_error: 0.2916 - val_loss: 13.4673 - val_mean_absolute_error: 2.8270
Epoch 512/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1856 - mean_absolute_error: 0.2512 - val_loss: 13.5554 - val_mean_absolute_error: 2.8709
Epoch 513/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1885 - mean_absolute_error: 0.2346 - val_loss: 13.2373 - val_mean_absolute_error: 2.7656
Epoch 514/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2982 - mean_absolute_error: 0.2934 - val_loss: 13.7629 - val_mean_absolute_error: 2.9334
Epoch 515/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3354 - mean_absolute_error: 0.3741 - val_loss: 13.4249 - val_mean_absolute_error: 2.8261
Epoch 516/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2000 - mean_absolute_error: 0.2969 - val_loss: 12.9408 - val_mean_absolute_error: 2.7939
Epoch 517/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3797 - mean_absolute_error: 0.3391 - val_loss: 13.6104 - val_mean_absolute_error: 2.8716
Epoch 518/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2902 - mean_absolute_error: 0.3274 - val_loss: 13.5852 - val_mean_absolute_error: 2.8660
Epoch 519/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2429 - mean_absolute_error: 0.3200 - val_loss: 12.8229 - val_mean_absolute_error: 2.7857
Epoch 520/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1935 - mean_absolute_error: 0.2535 - val_loss: 13.6991 - val_mean_absolute_error: 2.9427
Epoch 521/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1896 - mean_absolute_error: 0.2770 - val_loss: 13.4141 - val_mean_absolute_error: 2.8294
Epoch 522/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2368 - mean_absolute_error: 0.2893 - val_loss: 13.0254 - val_mean_absolute_error: 2.8138
Epoch 523/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3257 - mean_absolute_error: 0.3143 - val_loss: 12.9925 - val_mean_absolute_error: 2.8348
Epoch 524/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2698 - mean_absolute_error: 0.3159 - val_loss: 13.7805 - val_mean_absolute_error: 2.8529
Epoch 525/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2574 - mean_absolute_error: 0.3090 - val_loss: 13.3376 - val_mean_absolute_error: 2.8735
Epoch 526/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1819 - mean_absolute_error: 0.2725 - val_loss: 13.1385 - val_mean_absolute_error: 2.8149
Epoch 527/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1870 - mean_absolute_error: 0.2695 - val_loss: 13.6056 - val_mean_absolute_error: 2.8989
Epoch 528/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.1766 - mean_absolute_error: 0.2444 - val_loss: 13.2049 - val_mean_absolute_error: 2.8265
Epoch 529/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1621 - mean_absolute_error: 0.2409 - val_loss: 13.0746 - val_mean_absolute_error: 2.8190
Epoch 530/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1992 - mean_absolute_error: 0.2805 - val_loss: 13.7411 - val_mean_absolute_error: 2.9401
Epoch 531/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2245 - mean_absolute_error: 0.3024 - val_loss: 13.6451 - val_mean_absolute_error: 2.8947
Epoch 532/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3343 - mean_absolute_error: 0.3046 - val_loss: 13.6957 - val_mean_absolute_error: 2.8091
Epoch 533/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3788 - mean_absolute_error: 0.3724 - val_loss: 12.6701 - val_mean_absolute_error: 2.7869
Epoch 534/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2665 - mean_absolute_error: 0.3404 - val_loss: 13.6235 - val_mean_absolute_error: 2.8976
Epoch 535/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2448 - mean_absolute_error: 0.3424 - val_loss: 13.3336 - val_mean_absolute_error: 2.8345
Epoch 536/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1824 - mean_absolute_error: 0.2541 - val_loss: 12.8287 - val_mean_absolute_error: 2.7710
Epoch 537/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1608 - mean_absolute_error: 0.2458 - val_loss: 13.4785 - val_mean_absolute_error: 2.8844
Epoch 538/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2285 - mean_absolute_error: 0.2760 - val_loss: 13.3629 - val_mean_absolute_error: 2.8026
Epoch 539/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2822 - mean_absolute_error: 0.2948 - val_loss: 13.1528 - val_mean_absolute_error: 2.7412
Epoch 540/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3876 - mean_absolute_error: 0.3431 - val_loss: 13.1033 - val_mean_absolute_error: 2.7873
Epoch 541/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3246 - mean_absolute_error: 0.3429 - val_loss: 13.2865 - val_mean_absolute_error: 2.8243
Epoch 542/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2625 - mean_absolute_error: 0.3274 - val_loss: 13.5174 - val_mean_absolute_error: 2.8326
Epoch 543/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2322 - mean_absolute_error: 0.3074 - val_loss: 13.4542 - val_mean_absolute_error: 2.8925
Epoch 544/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1785 - mean_absolute_error: 0.2591 - val_loss: 13.3131 - val_mean_absolute_error: 2.7785
Epoch 545/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1922 - mean_absolute_error: 0.2710 - val_loss: 12.7267 - val_mean_absolute_error: 2.7568
Epoch 546/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1721 - mean_absolute_error: 0.2492 - val_loss: 13.6111 - val_mean_absolute_error: 2.9058
Epoch 547/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1862 - mean_absolute_error: 0.2754 - val_loss: 12.8712 - val_mean_absolute_error: 2.7893
Epoch 548/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1972 - mean_absolute_error: 0.2405 - val_loss: 13.3051 - val_mean_absolute_error: 2.8470
Epoch 549/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7661 - mean_absolute_error: 0.4052 - val_loss: 13.9286 - val_mean_absolute_error: 2.7932
Epoch 550/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5331 - mean_absolute_error: 0.4749 - val_loss: 12.4985 - val_mean_absolute_error: 2.7828
Epoch 551/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3779 - mean_absolute_error: 0.4186 - val_loss: 13.0363 - val_mean_absolute_error: 2.8741
Epoch 552/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3506 - mean_absolute_error: 0.3902 - val_loss: 12.7053 - val_mean_absolute_error: 2.8297
Epoch 553/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3345 - mean_absolute_error: 0.3782 - val_loss: 13.0097 - val_mean_absolute_error: 2.8610
Epoch 554/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2551 - mean_absolute_error: 0.3404 - val_loss: 13.5527 - val_mean_absolute_error: 2.8888
Epoch 555/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2593 - mean_absolute_error: 0.3340 - val_loss: 13.3368 - val_mean_absolute_error: 2.8975
Epoch 556/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1997 - mean_absolute_error: 0.2849 - val_loss: 12.9478 - val_mean_absolute_error: 2.8213
Epoch 557/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1624 - mean_absolute_error: 0.2604 - val_loss: 12.8950 - val_mean_absolute_error: 2.7986
Epoch 558/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2633 - mean_absolute_error: 0.2784 - val_loss: 13.6323 - val_mean_absolute_error: 2.9201
Epoch 559/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2048 - mean_absolute_error: 0.2928 - val_loss: 12.6261 - val_mean_absolute_error: 2.7828
Epoch 560/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1480 - mean_absolute_error: 0.2472 - val_loss: 13.0144 - val_mean_absolute_error: 2.8075
Epoch 561/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1552 - mean_absolute_error: 0.2378 - val_loss: 13.2516 - val_mean_absolute_error: 2.8548
Epoch 562/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1234 - mean_absolute_error: 0.2053 - val_loss: 13.0763 - val_mean_absolute_error: 2.8834
Epoch 563/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1214 - mean_absolute_error: 0.1908 - val_loss: 13.1710 - val_mean_absolute_error: 2.8365
Epoch 564/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1289 - mean_absolute_error: 0.1864 - val_loss: 13.2444 - val_mean_absolute_error: 2.8501
Epoch 565/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1068 - mean_absolute_error: 0.1551 - val_loss: 13.1563 - val_mean_absolute_error: 2.8476
Epoch 566/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1301 - mean_absolute_error: 0.1760 - val_loss: 13.1512 - val_mean_absolute_error: 2.8680
Epoch 567/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1471 - mean_absolute_error: 0.1999 - val_loss: 13.3427 - val_mean_absolute_error: 2.8590
Epoch 568/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2647 - mean_absolute_error: 0.2583 - val_loss: 13.5693 - val_mean_absolute_error: 2.8943
Epoch 569/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2024 - mean_absolute_error: 0.2927 - val_loss: 13.6833 - val_mean_absolute_error: 2.9474
Epoch 570/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2106 - mean_absolute_error: 0.3130 - val_loss: 13.3581 - val_mean_absolute_error: 2.8687
Epoch 571/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1525 - mean_absolute_error: 0.2302 - val_loss: 13.6374 - val_mean_absolute_error: 2.8922
Epoch 572/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1508 - mean_absolute_error: 0.2357 - val_loss: 13.3458 - val_mean_absolute_error: 2.8461
Epoch 573/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1192 - mean_absolute_error: 0.1999 - val_loss: 13.5945 - val_mean_absolute_error: 2.9435
Epoch 574/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1267 - mean_absolute_error: 0.2144 - val_loss: 13.3606 - val_mean_absolute_error: 2.8644
Epoch 575/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1116 - mean_absolute_error: 0.1788 - val_loss: 13.2824 - val_mean_absolute_error: 2.8586
Epoch 576/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1138 - mean_absolute_error: 0.1819 - val_loss: 13.1591 - val_mean_absolute_error: 2.8366
Epoch 577/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1123 - mean_absolute_error: 0.1884 - val_loss: 13.4510 - val_mean_absolute_error: 2.9106
Epoch 578/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.1346 - mean_absolute_error: 0.2111 - val_loss: 13.2146 - val_mean_absolute_error: 2.8403
Epoch 579/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1208 - mean_absolute_error: 0.1902 - val_loss: 13.2890 - val_mean_absolute_error: 2.8573
Epoch 580/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1333 - mean_absolute_error: 0.2057 - val_loss: 13.4400 - val_mean_absolute_error: 2.8822
Epoch 581/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1717 - mean_absolute_error: 0.2050 - val_loss: 13.2070 - val_mean_absolute_error: 2.8630
Epoch 582/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1150 - mean_absolute_error: 0.1815 - val_loss: 13.4633 - val_mean_absolute_error: 2.8889
Epoch 583/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1245 - mean_absolute_error: 0.2021 - val_loss: 13.2697 - val_mean_absolute_error: 2.8273
Epoch 584/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1290 - mean_absolute_error: 0.1938 - val_loss: 13.7150 - val_mean_absolute_error: 2.9140
Epoch 585/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1311 - mean_absolute_error: 0.2143 - val_loss: 13.5167 - val_mean_absolute_error: 2.8719
Epoch 586/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.2192 - mean_absolute_error: 0.2677 - val_loss: 13.5373 - val_mean_absolute_error: 2.8997
Epoch 587/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.2519 - mean_absolute_error: 0.2973 - val_loss: 12.8709 - val_mean_absolute_error: 2.8006
Epoch 588/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.2240 - mean_absolute_error: 0.3227 - val_loss: 13.9189 - val_mean_absolute_error: 2.9682
Epoch 589/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.2964 - mean_absolute_error: 0.3803 - val_loss: 13.6907 - val_mean_absolute_error: 2.8981
Epoch 590/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.2662 - mean_absolute_error: 0.3442 - val_loss: 12.6306 - val_mean_absolute_error: 2.7732
Epoch 591/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.3651 - mean_absolute_error: 0.3967 - val_loss: 13.4874 - val_mean_absolute_error: 2.8437
Epoch 592/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2131 - mean_absolute_error: 0.3317 - val_loss: 13.8028 - val_mean_absolute_error: 2.8976
Epoch 593/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3310 - mean_absolute_error: 0.3477 - val_loss: 13.5262 - val_mean_absolute_error: 2.9016
Epoch 594/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2514 - mean_absolute_error: 0.3417 - val_loss: 12.9908 - val_mean_absolute_error: 2.7785
Epoch 595/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2283 - mean_absolute_error: 0.3287 - val_loss: 13.2383 - val_mean_absolute_error: 2.8624
Epoch 596/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1961 - mean_absolute_error: 0.2896 - val_loss: 12.9689 - val_mean_absolute_error: 2.8502
Epoch 597/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1995 - mean_absolute_error: 0.2845 - val_loss: 13.3882 - val_mean_absolute_error: 2.9036
Epoch 598/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2053 - mean_absolute_error: 0.2744 - val_loss: 13.4927 - val_mean_absolute_error: 2.8562
Epoch 599/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2179 - mean_absolute_error: 0.3089 - val_loss: 13.3133 - val_mean_absolute_error: 2.8424
Epoch 600/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1956 - mean_absolute_error: 0.3060 - val_loss: 13.5312 - val_mean_absolute_error: 2.8950
Epoch 601/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1607 - mean_absolute_error: 0.2453 - val_loss: 13.6336 - val_mean_absolute_error: 2.9017
Epoch 602/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2083 - mean_absolute_error: 0.2840 - val_loss: 13.0905 - val_mean_absolute_error: 2.8434
Epoch 603/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3272 - mean_absolute_error: 0.3104 - val_loss: 13.0850 - val_mean_absolute_error: 2.8776
Epoch 604/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2024 - mean_absolute_error: 0.2811 - val_loss: 13.0505 - val_mean_absolute_error: 2.8625
Epoch 605/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2376 - mean_absolute_error: 0.2918 - val_loss: 13.3505 - val_mean_absolute_error: 2.8988
Epoch 606/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2268 - mean_absolute_error: 0.2834 - val_loss: 13.0473 - val_mean_absolute_error: 2.8520
Epoch 607/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1902 - mean_absolute_error: 0.2579 - val_loss: 13.4770 - val_mean_absolute_error: 2.9174
Epoch 608/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5006 - mean_absolute_error: 0.3074 - val_loss: 12.8826 - val_mean_absolute_error: 2.8101
Epoch 609/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.4399 - mean_absolute_error: 0.4044 - val_loss: 13.0814 - val_mean_absolute_error: 2.9117
Epoch 610/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.2394 - mean_absolute_error: 0.6597 - val_loss: 14.0580 - val_mean_absolute_error: 2.9346
Epoch 611/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1122 - mean_absolute_error: 0.6137 - val_loss: 12.6906 - val_mean_absolute_error: 2.7956
Epoch 612/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8638 - mean_absolute_error: 0.6189 - val_loss: 12.5440 - val_mean_absolute_error: 2.6015
Epoch 613/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4981 - mean_absolute_error: 0.5079 - val_loss: 13.7693 - val_mean_absolute_error: 3.0086
Epoch 614/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7176 - mean_absolute_error: 0.5401 - val_loss: 12.9129 - val_mean_absolute_error: 2.8637
Epoch 615/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.2386 - mean_absolute_error: 0.5901 - val_loss: 13.3238 - val_mean_absolute_error: 2.9013
Epoch 616/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6534 - mean_absolute_error: 0.5985 - val_loss: 12.8090 - val_mean_absolute_error: 2.8180
Epoch 617/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4193 - mean_absolute_error: 0.4498 - val_loss: 13.9525 - val_mean_absolute_error: 2.9285
Epoch 618/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4582 - mean_absolute_error: 0.4528 - val_loss: 12.7366 - val_mean_absolute_error: 2.7974
Epoch 619/1000
7/7 [==============================] - 0s 35ms/step - loss: 0.3216 - mean_absolute_error: 0.3831 - val_loss: 12.5660 - val_mean_absolute_error: 2.6392
Epoch 620/1000
7/7 [==============================] - 0s 37ms/step - loss: 0.3511 - mean_absolute_error: 0.3786 - val_loss: 13.6184 - val_mean_absolute_error: 2.9265
Epoch 621/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.6129 - mean_absolute_error: 0.4072 - val_loss: 13.4308 - val_mean_absolute_error: 2.8376
Epoch 622/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3136 - mean_absolute_error: 0.3896 - val_loss: 13.4255 - val_mean_absolute_error: 2.8452
Epoch 623/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3436 - mean_absolute_error: 0.4219 - val_loss: 12.9026 - val_mean_absolute_error: 2.8584
Epoch 624/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3645 - mean_absolute_error: 0.4143 - val_loss: 13.3924 - val_mean_absolute_error: 2.8190
Epoch 625/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.6063 - mean_absolute_error: 0.4567 - val_loss: 12.9680 - val_mean_absolute_error: 2.7762
Epoch 626/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3578 - mean_absolute_error: 0.4214 - val_loss: 11.7558 - val_mean_absolute_error: 2.6411
Epoch 627/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3852 - mean_absolute_error: 0.4348 - val_loss: 12.9726 - val_mean_absolute_error: 2.8274
Epoch 628/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2669 - mean_absolute_error: 0.3745 - val_loss: 14.0141 - val_mean_absolute_error: 2.9424
Epoch 629/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8400 - mean_absolute_error: 0.4898 - val_loss: 12.1444 - val_mean_absolute_error: 2.6408
Epoch 630/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5986 - mean_absolute_error: 0.5684 - val_loss: 12.0960 - val_mean_absolute_error: 2.7052
Epoch 631/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7653 - mean_absolute_error: 0.5794 - val_loss: 13.3726 - val_mean_absolute_error: 2.7872
Epoch 632/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7343 - mean_absolute_error: 0.6275 - val_loss: 11.4175 - val_mean_absolute_error: 2.5534
Epoch 633/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9324 - mean_absolute_error: 0.6888 - val_loss: 11.8571 - val_mean_absolute_error: 2.6709
Epoch 634/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5717 - mean_absolute_error: 0.5515 - val_loss: 12.6594 - val_mean_absolute_error: 2.9007
Epoch 635/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.7710 - mean_absolute_error: 0.6507 - val_loss: 11.7763 - val_mean_absolute_error: 2.7337
Epoch 636/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.7046 - mean_absolute_error: 0.5912 - val_loss: 12.4490 - val_mean_absolute_error: 2.7305
Epoch 637/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9119 - mean_absolute_error: 0.5552 - val_loss: 13.1661 - val_mean_absolute_error: 2.8617
Epoch 638/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6068 - mean_absolute_error: 0.5850 - val_loss: 12.9403 - val_mean_absolute_error: 2.6694
Epoch 639/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.6167 - mean_absolute_error: 0.5305 - val_loss: 12.9742 - val_mean_absolute_error: 2.8822
Epoch 640/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3516 - mean_absolute_error: 0.4287 - val_loss: 12.4293 - val_mean_absolute_error: 2.7591
Epoch 641/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.3724 - mean_absolute_error: 0.4322 - val_loss: 12.0089 - val_mean_absolute_error: 2.7017
Epoch 642/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4297 - mean_absolute_error: 0.4244 - val_loss: 12.8968 - val_mean_absolute_error: 2.7654
Epoch 643/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2396 - mean_absolute_error: 0.3395 - val_loss: 12.3524 - val_mean_absolute_error: 2.7300
Epoch 644/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2006 - mean_absolute_error: 0.2907 - val_loss: 12.2105 - val_mean_absolute_error: 2.6710
Epoch 645/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1553 - mean_absolute_error: 0.2358 - val_loss: 12.3096 - val_mean_absolute_error: 2.6893
Epoch 646/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1745 - mean_absolute_error: 0.2579 - val_loss: 12.8198 - val_mean_absolute_error: 2.8115
Epoch 647/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2840 - mean_absolute_error: 0.2784 - val_loss: 12.0410 - val_mean_absolute_error: 2.7129
Epoch 648/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3425 - mean_absolute_error: 0.3136 - val_loss: 12.2375 - val_mean_absolute_error: 2.6802
Epoch 649/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2543 - mean_absolute_error: 0.2780 - val_loss: 12.2733 - val_mean_absolute_error: 2.7417
Epoch 650/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1501 - mean_absolute_error: 0.2353 - val_loss: 12.1072 - val_mean_absolute_error: 2.7088
Epoch 651/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1243 - mean_absolute_error: 0.2163 - val_loss: 11.8400 - val_mean_absolute_error: 2.6929
Epoch 652/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1623 - mean_absolute_error: 0.2346 - val_loss: 12.4446 - val_mean_absolute_error: 2.7581
Epoch 653/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2733 - mean_absolute_error: 0.2815 - val_loss: 12.2783 - val_mean_absolute_error: 2.6976
Epoch 654/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3494 - mean_absolute_error: 0.3678 - val_loss: 11.6442 - val_mean_absolute_error: 2.6893
Epoch 655/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2041 - mean_absolute_error: 0.3014 - val_loss: 12.1984 - val_mean_absolute_error: 2.7337
Epoch 656/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2441 - mean_absolute_error: 0.3032 - val_loss: 12.3574 - val_mean_absolute_error: 2.7595
Epoch 657/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2139 - mean_absolute_error: 0.3017 - val_loss: 12.1956 - val_mean_absolute_error: 2.6698
Epoch 658/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1866 - mean_absolute_error: 0.2588 - val_loss: 12.4755 - val_mean_absolute_error: 2.7933
Epoch 659/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5798 - mean_absolute_error: 0.4022 - val_loss: 12.9489 - val_mean_absolute_error: 2.7484
Epoch 660/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5540 - mean_absolute_error: 0.4464 - val_loss: 12.0505 - val_mean_absolute_error: 2.7761
Epoch 661/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4890 - mean_absolute_error: 0.4370 - val_loss: 12.0150 - val_mean_absolute_error: 2.6358
Epoch 662/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4522 - mean_absolute_error: 0.4556 - val_loss: 12.9469 - val_mean_absolute_error: 2.8029
Epoch 663/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5157 - mean_absolute_error: 0.4609 - val_loss: 12.5574 - val_mean_absolute_error: 2.8083
Epoch 664/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8589 - mean_absolute_error: 0.4827 - val_loss: 12.1941 - val_mean_absolute_error: 2.7637
Epoch 665/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7757 - mean_absolute_error: 0.4786 - val_loss: 12.0186 - val_mean_absolute_error: 2.6701
Epoch 666/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4144 - mean_absolute_error: 0.3967 - val_loss: 11.8065 - val_mean_absolute_error: 2.7315
Epoch 667/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5185 - mean_absolute_error: 0.4012 - val_loss: 12.1515 - val_mean_absolute_error: 2.7211
Epoch 668/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4876 - mean_absolute_error: 0.3879 - val_loss: 12.4548 - val_mean_absolute_error: 2.8448
Epoch 669/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2313 - mean_absolute_error: 0.3153 - val_loss: 12.2637 - val_mean_absolute_error: 2.7582
Epoch 670/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3173 - mean_absolute_error: 0.3102 - val_loss: 11.9896 - val_mean_absolute_error: 2.7798
Epoch 671/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2216 - mean_absolute_error: 0.3155 - val_loss: 12.2670 - val_mean_absolute_error: 2.7787
Epoch 672/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1816 - mean_absolute_error: 0.2812 - val_loss: 12.2173 - val_mean_absolute_error: 2.7886
Epoch 673/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2045 - mean_absolute_error: 0.2814 - val_loss: 11.4423 - val_mean_absolute_error: 2.6540
Epoch 674/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5847 - mean_absolute_error: 0.3098 - val_loss: 11.8195 - val_mean_absolute_error: 2.7296
Epoch 675/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3165 - mean_absolute_error: 0.2982 - val_loss: 12.4498 - val_mean_absolute_error: 2.7676
Epoch 676/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3405 - mean_absolute_error: 0.3367 - val_loss: 11.9110 - val_mean_absolute_error: 2.7346
Epoch 677/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2963 - mean_absolute_error: 0.3214 - val_loss: 11.4614 - val_mean_absolute_error: 2.6880
Epoch 678/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.2244 - mean_absolute_error: 0.3039 - val_loss: 11.8654 - val_mean_absolute_error: 2.6873
Epoch 679/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1748 - mean_absolute_error: 0.2607 - val_loss: 11.6102 - val_mean_absolute_error: 2.7073
Epoch 680/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1837 - mean_absolute_error: 0.2729 - val_loss: 11.5818 - val_mean_absolute_error: 2.6577
Epoch 681/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1887 - mean_absolute_error: 0.2887 - val_loss: 11.5256 - val_mean_absolute_error: 2.7013
Epoch 682/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1520 - mean_absolute_error: 0.2479 - val_loss: 11.8201 - val_mean_absolute_error: 2.7091
Epoch 683/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.1376 - mean_absolute_error: 0.2353 - val_loss: 11.7590 - val_mean_absolute_error: 2.7335
Epoch 684/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1488 - mean_absolute_error: 0.2529 - val_loss: 12.2691 - val_mean_absolute_error: 2.7577
Epoch 685/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1915 - mean_absolute_error: 0.2732 - val_loss: 11.8043 - val_mean_absolute_error: 2.6870
Epoch 686/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1749 - mean_absolute_error: 0.2646 - val_loss: 12.3878 - val_mean_absolute_error: 2.8576
Epoch 687/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2301 - mean_absolute_error: 0.3059 - val_loss: 12.1442 - val_mean_absolute_error: 2.7079
Epoch 688/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2263 - mean_absolute_error: 0.3172 - val_loss: 12.0225 - val_mean_absolute_error: 2.7631
Epoch 689/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3680 - mean_absolute_error: 0.4208 - val_loss: 12.2779 - val_mean_absolute_error: 2.7726
Epoch 690/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3534 - mean_absolute_error: 0.4163 - val_loss: 11.9325 - val_mean_absolute_error: 2.8562
Epoch 691/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3618 - mean_absolute_error: 0.4171 - val_loss: 11.8319 - val_mean_absolute_error: 2.7052
Epoch 692/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2508 - mean_absolute_error: 0.3367 - val_loss: 11.9145 - val_mean_absolute_error: 2.7610
Epoch 693/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1876 - mean_absolute_error: 0.2889 - val_loss: 11.3701 - val_mean_absolute_error: 2.6926
Epoch 694/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1715 - mean_absolute_error: 0.2916 - val_loss: 11.8786 - val_mean_absolute_error: 2.6923
Epoch 695/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2126 - mean_absolute_error: 0.2668 - val_loss: 11.7010 - val_mean_absolute_error: 2.7227
Epoch 696/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1806 - mean_absolute_error: 0.2805 - val_loss: 12.1548 - val_mean_absolute_error: 2.7810
Epoch 697/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1781 - mean_absolute_error: 0.2647 - val_loss: 11.6120 - val_mean_absolute_error: 2.7476
Epoch 698/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1543 - mean_absolute_error: 0.2514 - val_loss: 11.6332 - val_mean_absolute_error: 2.6927
Epoch 699/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1301 - mean_absolute_error: 0.2281 - val_loss: 11.5381 - val_mean_absolute_error: 2.7224
Epoch 700/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1389 - mean_absolute_error: 0.2125 - val_loss: 11.6653 - val_mean_absolute_error: 2.6981
Epoch 701/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1658 - mean_absolute_error: 0.2464 - val_loss: 11.7218 - val_mean_absolute_error: 2.7147
Epoch 702/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1730 - mean_absolute_error: 0.2534 - val_loss: 11.4552 - val_mean_absolute_error: 2.6704
Epoch 703/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1598 - mean_absolute_error: 0.2500 - val_loss: 12.1941 - val_mean_absolute_error: 2.7815
Epoch 704/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1655 - mean_absolute_error: 0.2545 - val_loss: 12.3536 - val_mean_absolute_error: 2.8016
Epoch 705/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1462 - mean_absolute_error: 0.2379 - val_loss: 11.9855 - val_mean_absolute_error: 2.7170
Epoch 706/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1123 - mean_absolute_error: 0.1964 - val_loss: 11.8417 - val_mean_absolute_error: 2.7128
Epoch 707/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1136 - mean_absolute_error: 0.2008 - val_loss: 11.8996 - val_mean_absolute_error: 2.7323
Epoch 708/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0942 - mean_absolute_error: 0.1668 - val_loss: 12.1136 - val_mean_absolute_error: 2.7832
Epoch 709/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1189 - mean_absolute_error: 0.2021 - val_loss: 11.4317 - val_mean_absolute_error: 2.6596
Epoch 710/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1128 - mean_absolute_error: 0.1973 - val_loss: 11.6737 - val_mean_absolute_error: 2.7408
Epoch 711/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1015 - mean_absolute_error: 0.1830 - val_loss: 11.9220 - val_mean_absolute_error: 2.7325
Epoch 712/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0995 - mean_absolute_error: 0.1770 - val_loss: 11.6589 - val_mean_absolute_error: 2.7120
Epoch 713/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1031 - mean_absolute_error: 0.1775 - val_loss: 11.8986 - val_mean_absolute_error: 2.7398
Epoch 714/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0961 - mean_absolute_error: 0.1537 - val_loss: 11.6518 - val_mean_absolute_error: 2.7314
Epoch 715/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0803 - mean_absolute_error: 0.1401 - val_loss: 11.7197 - val_mean_absolute_error: 2.7168
Epoch 716/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0788 - mean_absolute_error: 0.1250 - val_loss: 11.8253 - val_mean_absolute_error: 2.7264
Epoch 717/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0743 - mean_absolute_error: 0.1125 - val_loss: 11.8410 - val_mean_absolute_error: 2.7483
Epoch 718/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.0788 - mean_absolute_error: 0.1355 - val_loss: 11.7417 - val_mean_absolute_error: 2.7205
Epoch 719/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0811 - mean_absolute_error: 0.1346 - val_loss: 12.0186 - val_mean_absolute_error: 2.7726
Epoch 720/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0837 - mean_absolute_error: 0.1445 - val_loss: 11.9816 - val_mean_absolute_error: 2.7473
Epoch 721/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1001 - mean_absolute_error: 0.1748 - val_loss: 11.5752 - val_mean_absolute_error: 2.7134
Epoch 722/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0923 - mean_absolute_error: 0.1522 - val_loss: 11.6341 - val_mean_absolute_error: 2.6987
Epoch 723/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1329 - mean_absolute_error: 0.2288 - val_loss: 12.2222 - val_mean_absolute_error: 2.8107
Epoch 724/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1963 - mean_absolute_error: 0.2990 - val_loss: 12.2356 - val_mean_absolute_error: 2.7492
Epoch 725/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.2421 - mean_absolute_error: 0.3150 - val_loss: 11.4970 - val_mean_absolute_error: 2.6848
Epoch 726/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1752 - mean_absolute_error: 0.3061 - val_loss: 12.0477 - val_mean_absolute_error: 2.7919
Epoch 727/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1767 - mean_absolute_error: 0.2575 - val_loss: 11.9367 - val_mean_absolute_error: 2.7318
Epoch 728/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1428 - mean_absolute_error: 0.2303 - val_loss: 11.6728 - val_mean_absolute_error: 2.7505
Epoch 729/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1328 - mean_absolute_error: 0.2274 - val_loss: 11.5297 - val_mean_absolute_error: 2.6818
Epoch 730/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.1333 - mean_absolute_error: 0.2205 - val_loss: 11.8827 - val_mean_absolute_error: 2.7424
Epoch 731/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.1409 - mean_absolute_error: 0.2148 - val_loss: 11.6266 - val_mean_absolute_error: 2.7094
Epoch 732/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1283 - mean_absolute_error: 0.1953 - val_loss: 11.8602 - val_mean_absolute_error: 2.7609
Epoch 733/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1062 - mean_absolute_error: 0.1821 - val_loss: 11.8830 - val_mean_absolute_error: 2.7507
Epoch 734/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1119 - mean_absolute_error: 0.1819 - val_loss: 11.6271 - val_mean_absolute_error: 2.6857
Epoch 735/1000
7/7 [==============================] - 0s 36ms/step - loss: 0.0971 - mean_absolute_error: 0.1693 - val_loss: 11.9326 - val_mean_absolute_error: 2.7193
Epoch 736/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.0948 - mean_absolute_error: 0.1596 - val_loss: 11.7998 - val_mean_absolute_error: 2.7077
Epoch 737/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0871 - mean_absolute_error: 0.1451 - val_loss: 11.4200 - val_mean_absolute_error: 2.6882
Epoch 738/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1212 - mean_absolute_error: 0.1787 - val_loss: 11.6701 - val_mean_absolute_error: 2.7014
Epoch 739/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1013 - mean_absolute_error: 0.1578 - val_loss: 12.0857 - val_mean_absolute_error: 2.7351
Epoch 740/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1194 - mean_absolute_error: 0.1932 - val_loss: 11.7790 - val_mean_absolute_error: 2.7000
Epoch 741/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1020 - mean_absolute_error: 0.1619 - val_loss: 11.5642 - val_mean_absolute_error: 2.6889
Epoch 742/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0900 - mean_absolute_error: 0.1518 - val_loss: 11.9176 - val_mean_absolute_error: 2.7264
Epoch 743/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1242 - mean_absolute_error: 0.1635 - val_loss: 11.7117 - val_mean_absolute_error: 2.7157
Epoch 744/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0946 - mean_absolute_error: 0.1637 - val_loss: 11.7322 - val_mean_absolute_error: 2.6693
Epoch 745/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.1408 - mean_absolute_error: 0.1799 - val_loss: 12.0673 - val_mean_absolute_error: 2.7522
Epoch 746/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1360 - mean_absolute_error: 0.2165 - val_loss: 11.4167 - val_mean_absolute_error: 2.6733
Epoch 747/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1007 - mean_absolute_error: 0.1863 - val_loss: 11.6996 - val_mean_absolute_error: 2.7238
Epoch 748/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1132 - mean_absolute_error: 0.1875 - val_loss: 12.1282 - val_mean_absolute_error: 2.7728
Epoch 749/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1064 - mean_absolute_error: 0.1988 - val_loss: 11.7317 - val_mean_absolute_error: 2.6852
Epoch 750/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1072 - mean_absolute_error: 0.1854 - val_loss: 11.5699 - val_mean_absolute_error: 2.7165
Epoch 751/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1355 - mean_absolute_error: 0.1804 - val_loss: 11.6657 - val_mean_absolute_error: 2.7033
Epoch 752/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0892 - mean_absolute_error: 0.1546 - val_loss: 11.9178 - val_mean_absolute_error: 2.7368
Epoch 753/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1252 - mean_absolute_error: 0.1696 - val_loss: 11.5205 - val_mean_absolute_error: 2.6783
Epoch 754/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0866 - mean_absolute_error: 0.1480 - val_loss: 11.7737 - val_mean_absolute_error: 2.7218
Epoch 755/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0900 - mean_absolute_error: 0.1412 - val_loss: 11.8354 - val_mean_absolute_error: 2.7225
Epoch 756/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0911 - mean_absolute_error: 0.1490 - val_loss: 11.9975 - val_mean_absolute_error: 2.7730
Epoch 757/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0904 - mean_absolute_error: 0.1553 - val_loss: 11.7240 - val_mean_absolute_error: 2.7204
Epoch 758/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0971 - mean_absolute_error: 0.1457 - val_loss: 12.3583 - val_mean_absolute_error: 2.7925
Epoch 759/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1103 - mean_absolute_error: 0.1537 - val_loss: 11.9988 - val_mean_absolute_error: 2.7512
Epoch 760/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0918 - mean_absolute_error: 0.1436 - val_loss: 11.7432 - val_mean_absolute_error: 2.7250
Epoch 761/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1009 - mean_absolute_error: 0.1646 - val_loss: 11.6021 - val_mean_absolute_error: 2.6760
Epoch 762/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1074 - mean_absolute_error: 0.1663 - val_loss: 12.0018 - val_mean_absolute_error: 2.7352
Epoch 763/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0871 - mean_absolute_error: 0.1539 - val_loss: 11.7222 - val_mean_absolute_error: 2.7016
Epoch 764/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0872 - mean_absolute_error: 0.1522 - val_loss: 11.6489 - val_mean_absolute_error: 2.7139
Epoch 765/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0862 - mean_absolute_error: 0.1480 - val_loss: 11.7534 - val_mean_absolute_error: 2.6832
Epoch 766/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1023 - mean_absolute_error: 0.1679 - val_loss: 12.0155 - val_mean_absolute_error: 2.7441
Epoch 767/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1116 - mean_absolute_error: 0.2016 - val_loss: 11.6758 - val_mean_absolute_error: 2.7097
Epoch 768/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1433 - mean_absolute_error: 0.2052 - val_loss: 11.7611 - val_mean_absolute_error: 2.6864
Epoch 769/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1357 - mean_absolute_error: 0.2008 - val_loss: 11.7731 - val_mean_absolute_error: 2.6975
Epoch 770/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1082 - mean_absolute_error: 0.1828 - val_loss: 11.8797 - val_mean_absolute_error: 2.7169
Epoch 771/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0975 - mean_absolute_error: 0.1649 - val_loss: 11.9971 - val_mean_absolute_error: 2.7290
Epoch 772/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0980 - mean_absolute_error: 0.1695 - val_loss: 12.0701 - val_mean_absolute_error: 2.7749
Epoch 773/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1239 - mean_absolute_error: 0.1900 - val_loss: 11.5758 - val_mean_absolute_error: 2.6816
Epoch 774/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3032 - mean_absolute_error: 0.2931 - val_loss: 11.9959 - val_mean_absolute_error: 2.7522
Epoch 775/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5485 - mean_absolute_error: 0.3756 - val_loss: 11.7380 - val_mean_absolute_error: 2.7340
Epoch 776/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1832 - mean_absolute_error: 0.3054 - val_loss: 11.1794 - val_mean_absolute_error: 2.5185
Epoch 777/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2214 - mean_absolute_error: 0.2693 - val_loss: 12.0110 - val_mean_absolute_error: 2.7313
Epoch 778/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2281 - mean_absolute_error: 0.2924 - val_loss: 11.5895 - val_mean_absolute_error: 2.6658
Epoch 779/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6466 - mean_absolute_error: 0.4547 - val_loss: 12.4876 - val_mean_absolute_error: 2.8670
Epoch 780/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4514 - mean_absolute_error: 0.4534 - val_loss: 12.6957 - val_mean_absolute_error: 2.8498
Epoch 781/1000
7/7 [==============================] - 0s 43ms/step - loss: 0.4414 - mean_absolute_error: 0.4412 - val_loss: 10.9248 - val_mean_absolute_error: 2.6706
Epoch 782/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3948 - mean_absolute_error: 0.4219 - val_loss: 11.4883 - val_mean_absolute_error: 2.6665
Epoch 783/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4646 - mean_absolute_error: 0.4927 - val_loss: 11.7875 - val_mean_absolute_error: 2.6544
Epoch 784/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4200 - mean_absolute_error: 0.4563 - val_loss: 12.5631 - val_mean_absolute_error: 2.8973
Epoch 785/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2499 - mean_absolute_error: 0.3551 - val_loss: 12.3716 - val_mean_absolute_error: 2.7311
Epoch 786/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2709 - mean_absolute_error: 0.3635 - val_loss: 11.8565 - val_mean_absolute_error: 2.7020
Epoch 787/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2928 - mean_absolute_error: 0.3688 - val_loss: 12.0482 - val_mean_absolute_error: 2.8045
Epoch 788/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3738 - mean_absolute_error: 0.4025 - val_loss: 12.2408 - val_mean_absolute_error: 2.7844
Epoch 789/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2440 - mean_absolute_error: 0.3502 - val_loss: 11.5000 - val_mean_absolute_error: 2.7260
Epoch 790/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1867 - mean_absolute_error: 0.2906 - val_loss: 11.6427 - val_mean_absolute_error: 2.7058
Epoch 791/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1620 - mean_absolute_error: 0.2567 - val_loss: 12.2835 - val_mean_absolute_error: 2.8486
Epoch 792/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2075 - mean_absolute_error: 0.2953 - val_loss: 12.2096 - val_mean_absolute_error: 2.7930
Epoch 793/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1510 - mean_absolute_error: 0.2539 - val_loss: 11.7802 - val_mean_absolute_error: 2.7412
Epoch 794/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1175 - mean_absolute_error: 0.1975 - val_loss: 11.9528 - val_mean_absolute_error: 2.7637
Epoch 795/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1155 - mean_absolute_error: 0.2043 - val_loss: 11.3747 - val_mean_absolute_error: 2.6927
Epoch 796/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1079 - mean_absolute_error: 0.2006 - val_loss: 11.7404 - val_mean_absolute_error: 2.7448
Epoch 797/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1207 - mean_absolute_error: 0.2146 - val_loss: 11.8261 - val_mean_absolute_error: 2.7702
Epoch 798/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1018 - mean_absolute_error: 0.1891 - val_loss: 11.5953 - val_mean_absolute_error: 2.7033
Epoch 799/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1011 - mean_absolute_error: 0.1784 - val_loss: 11.7294 - val_mean_absolute_error: 2.7315
Epoch 800/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0968 - mean_absolute_error: 0.1680 - val_loss: 11.5593 - val_mean_absolute_error: 2.6847
Epoch 801/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0932 - mean_absolute_error: 0.1652 - val_loss: 11.3256 - val_mean_absolute_error: 2.6769
Epoch 802/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0907 - mean_absolute_error: 0.1607 - val_loss: 11.5700 - val_mean_absolute_error: 2.7000
Epoch 803/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0889 - mean_absolute_error: 0.1553 - val_loss: 11.8075 - val_mean_absolute_error: 2.7738
Epoch 804/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0852 - mean_absolute_error: 0.1507 - val_loss: 11.4806 - val_mean_absolute_error: 2.6928
Epoch 805/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0858 - mean_absolute_error: 0.1423 - val_loss: 11.4929 - val_mean_absolute_error: 2.6863
Epoch 806/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1083 - mean_absolute_error: 0.1762 - val_loss: 11.8160 - val_mean_absolute_error: 2.7771
Epoch 807/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0942 - mean_absolute_error: 0.1632 - val_loss: 11.7538 - val_mean_absolute_error: 2.7182
Epoch 808/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0911 - mean_absolute_error: 0.1444 - val_loss: 11.6864 - val_mean_absolute_error: 2.6873
Epoch 809/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0908 - mean_absolute_error: 0.1445 - val_loss: 11.7477 - val_mean_absolute_error: 2.7365
Epoch 810/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0879 - mean_absolute_error: 0.1491 - val_loss: 11.8759 - val_mean_absolute_error: 2.7596
Epoch 811/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0854 - mean_absolute_error: 0.1363 - val_loss: 11.3779 - val_mean_absolute_error: 2.6864
Epoch 812/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0703 - mean_absolute_error: 0.1379 - val_loss: 11.4180 - val_mean_absolute_error: 2.6641
Epoch 813/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1538 - mean_absolute_error: 0.1543 - val_loss: 11.7217 - val_mean_absolute_error: 2.7357
Epoch 814/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1166 - mean_absolute_error: 0.1615 - val_loss: 11.6232 - val_mean_absolute_error: 2.7016
Epoch 815/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0942 - mean_absolute_error: 0.1706 - val_loss: 11.3200 - val_mean_absolute_error: 2.6407
Epoch 816/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2663 - mean_absolute_error: 0.1959 - val_loss: 11.7527 - val_mean_absolute_error: 2.7110
Epoch 817/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2337 - mean_absolute_error: 0.2734 - val_loss: 11.9703 - val_mean_absolute_error: 2.7928
Epoch 818/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2595 - mean_absolute_error: 0.2859 - val_loss: 11.3873 - val_mean_absolute_error: 2.6923
Epoch 819/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2906 - mean_absolute_error: 0.3652 - val_loss: 12.7168 - val_mean_absolute_error: 2.7942
Epoch 820/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3030 - mean_absolute_error: 0.3818 - val_loss: 12.0828 - val_mean_absolute_error: 2.8195
Epoch 821/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3029 - mean_absolute_error: 0.3606 - val_loss: 12.2968 - val_mean_absolute_error: 2.8513
Epoch 822/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2775 - mean_absolute_error: 0.3605 - val_loss: 11.9972 - val_mean_absolute_error: 2.7796
Epoch 823/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2060 - mean_absolute_error: 0.2923 - val_loss: 11.6186 - val_mean_absolute_error: 2.7407
Epoch 824/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2326 - mean_absolute_error: 0.3348 - val_loss: 12.6261 - val_mean_absolute_error: 2.8159
Epoch 825/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2084 - mean_absolute_error: 0.2944 - val_loss: 12.1392 - val_mean_absolute_error: 2.7915
Epoch 826/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2926 - mean_absolute_error: 0.3466 - val_loss: 12.0025 - val_mean_absolute_error: 2.7241
Epoch 827/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2140 - mean_absolute_error: 0.3243 - val_loss: 12.2041 - val_mean_absolute_error: 2.7632
Epoch 828/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2398 - mean_absolute_error: 0.3228 - val_loss: 10.9210 - val_mean_absolute_error: 2.5942
Epoch 829/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2055 - mean_absolute_error: 0.3019 - val_loss: 11.4749 - val_mean_absolute_error: 2.6808
Epoch 830/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2071 - mean_absolute_error: 0.3145 - val_loss: 11.6667 - val_mean_absolute_error: 2.6814
Epoch 831/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1570 - mean_absolute_error: 0.2620 - val_loss: 12.1388 - val_mean_absolute_error: 2.8542
Epoch 832/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.1800 - mean_absolute_error: 0.2927 - val_loss: 11.7060 - val_mean_absolute_error: 2.6066
Epoch 833/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1960 - mean_absolute_error: 0.3046 - val_loss: 11.5922 - val_mean_absolute_error: 2.7404
Epoch 834/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1673 - mean_absolute_error: 0.2873 - val_loss: 11.1601 - val_mean_absolute_error: 2.6332
Epoch 835/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1370 - mean_absolute_error: 0.2356 - val_loss: 11.6773 - val_mean_absolute_error: 2.7463
Epoch 836/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1441 - mean_absolute_error: 0.2452 - val_loss: 11.9831 - val_mean_absolute_error: 2.7799
Epoch 837/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2597 - mean_absolute_error: 0.3221 - val_loss: 11.7070 - val_mean_absolute_error: 2.7814
Epoch 838/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6480 - mean_absolute_error: 0.5027 - val_loss: 10.9174 - val_mean_absolute_error: 2.6252
Epoch 839/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7726 - mean_absolute_error: 0.5586 - val_loss: 13.1511 - val_mean_absolute_error: 2.9712
Epoch 840/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7652 - mean_absolute_error: 0.6567 - val_loss: 11.4179 - val_mean_absolute_error: 2.6414
Epoch 841/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7790 - mean_absolute_error: 0.6483 - val_loss: 11.5637 - val_mean_absolute_error: 2.5780
Epoch 842/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.2285 - mean_absolute_error: 0.7608 - val_loss: 11.6899 - val_mean_absolute_error: 2.7881
Epoch 843/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2613 - mean_absolute_error: 0.8221 - val_loss: 11.8847 - val_mean_absolute_error: 2.8106
Epoch 844/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7458 - mean_absolute_error: 0.6396 - val_loss: 11.8500 - val_mean_absolute_error: 2.6366
Epoch 845/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5024 - mean_absolute_error: 0.8492 - val_loss: 14.8769 - val_mean_absolute_error: 3.2543
Epoch 846/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.5585 - mean_absolute_error: 1.1759 - val_loss: 11.5997 - val_mean_absolute_error: 2.4273
Epoch 847/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.6243 - mean_absolute_error: 1.0750 - val_loss: 12.4888 - val_mean_absolute_error: 2.6016
Epoch 848/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.3481 - mean_absolute_error: 0.9913 - val_loss: 13.7038 - val_mean_absolute_error: 2.8668
Epoch 849/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.7729 - mean_absolute_error: 1.2525 - val_loss: 10.8959 - val_mean_absolute_error: 2.3905
Epoch 850/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.6002 - mean_absolute_error: 1.0872 - val_loss: 12.8847 - val_mean_absolute_error: 2.7580
Epoch 851/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9402 - mean_absolute_error: 0.9772 - val_loss: 10.9627 - val_mean_absolute_error: 2.4820
Epoch 852/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.4753 - mean_absolute_error: 0.9238 - val_loss: 11.0020 - val_mean_absolute_error: 2.3537
Epoch 853/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0666 - mean_absolute_error: 0.8074 - val_loss: 14.0335 - val_mean_absolute_error: 2.8931
Epoch 854/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.3020 - mean_absolute_error: 0.7664 - val_loss: 10.5357 - val_mean_absolute_error: 2.3920
Epoch 855/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.7782 - mean_absolute_error: 0.6480 - val_loss: 11.9646 - val_mean_absolute_error: 2.7982
Epoch 856/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5433 - mean_absolute_error: 0.5303 - val_loss: 11.5077 - val_mean_absolute_error: 2.6046
Epoch 857/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4949 - mean_absolute_error: 0.5165 - val_loss: 11.6285 - val_mean_absolute_error: 2.7369
Epoch 858/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4682 - mean_absolute_error: 0.4758 - val_loss: 11.9551 - val_mean_absolute_error: 2.6649
Epoch 859/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4984 - mean_absolute_error: 0.4447 - val_loss: 13.7635 - val_mean_absolute_error: 2.8224
Epoch 860/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4281 - mean_absolute_error: 0.4095 - val_loss: 11.3838 - val_mean_absolute_error: 2.6373
Epoch 861/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3220 - mean_absolute_error: 0.3987 - val_loss: 11.9609 - val_mean_absolute_error: 2.7958
Epoch 862/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2188 - mean_absolute_error: 0.3105 - val_loss: 11.4656 - val_mean_absolute_error: 2.6061
Epoch 863/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2203 - mean_absolute_error: 0.3223 - val_loss: 11.8355 - val_mean_absolute_error: 2.6920
Epoch 864/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1652 - mean_absolute_error: 0.2703 - val_loss: 11.0199 - val_mean_absolute_error: 2.5864
Epoch 865/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1442 - mean_absolute_error: 0.2342 - val_loss: 11.4595 - val_mean_absolute_error: 2.6296
Epoch 866/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1363 - mean_absolute_error: 0.2221 - val_loss: 11.0560 - val_mean_absolute_error: 2.6027
Epoch 867/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.1212 - mean_absolute_error: 0.1971 - val_loss: 11.1946 - val_mean_absolute_error: 2.5886
Epoch 868/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1135 - mean_absolute_error: 0.1942 - val_loss: 11.4531 - val_mean_absolute_error: 2.6415
Epoch 869/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1039 - mean_absolute_error: 0.1749 - val_loss: 11.4406 - val_mean_absolute_error: 2.6381
Epoch 870/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.0900 - mean_absolute_error: 0.1533 - val_loss: 11.2964 - val_mean_absolute_error: 2.6392
Epoch 871/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.0902 - mean_absolute_error: 0.1494 - val_loss: 11.1860 - val_mean_absolute_error: 2.5987
Epoch 872/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.0884 - mean_absolute_error: 0.1444 - val_loss: 11.2208 - val_mean_absolute_error: 2.6116
Epoch 873/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0922 - mean_absolute_error: 0.1457 - val_loss: 11.2350 - val_mean_absolute_error: 2.6099
Epoch 874/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1107 - mean_absolute_error: 0.1596 - val_loss: 11.1943 - val_mean_absolute_error: 2.6204
Epoch 875/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0997 - mean_absolute_error: 0.1618 - val_loss: 11.2595 - val_mean_absolute_error: 2.6082
Epoch 876/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0946 - mean_absolute_error: 0.1572 - val_loss: 11.2322 - val_mean_absolute_error: 2.6253
Epoch 877/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0863 - mean_absolute_error: 0.1384 - val_loss: 11.4147 - val_mean_absolute_error: 2.6357
Epoch 878/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0937 - mean_absolute_error: 0.1511 - val_loss: 11.1506 - val_mean_absolute_error: 2.6004
Epoch 879/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0941 - mean_absolute_error: 0.1561 - val_loss: 11.3427 - val_mean_absolute_error: 2.6211
Epoch 880/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0881 - mean_absolute_error: 0.1428 - val_loss: 11.1204 - val_mean_absolute_error: 2.5992
Epoch 881/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0846 - mean_absolute_error: 0.1413 - val_loss: 11.2999 - val_mean_absolute_error: 2.6273
Epoch 882/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.0870 - mean_absolute_error: 0.1408 - val_loss: 11.1404 - val_mean_absolute_error: 2.6134
Epoch 883/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0811 - mean_absolute_error: 0.1370 - val_loss: 11.1944 - val_mean_absolute_error: 2.6101
Epoch 884/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0785 - mean_absolute_error: 0.1285 - val_loss: 11.2401 - val_mean_absolute_error: 2.6310
Epoch 885/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0862 - mean_absolute_error: 0.1407 - val_loss: 11.3461 - val_mean_absolute_error: 2.6313
Epoch 886/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.0840 - mean_absolute_error: 0.1380 - val_loss: 11.1891 - val_mean_absolute_error: 2.6169
Epoch 887/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1035 - mean_absolute_error: 0.1595 - val_loss: 11.3696 - val_mean_absolute_error: 2.6307
Epoch 888/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0851 - mean_absolute_error: 0.1571 - val_loss: 10.9426 - val_mean_absolute_error: 2.5619
Epoch 889/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1604 - mean_absolute_error: 0.1857 - val_loss: 11.0259 - val_mean_absolute_error: 2.5606
Epoch 890/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0893 - mean_absolute_error: 0.1486 - val_loss: 11.2509 - val_mean_absolute_error: 2.6132
Epoch 891/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0861 - mean_absolute_error: 0.1529 - val_loss: 11.2617 - val_mean_absolute_error: 2.6195
Epoch 892/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0815 - mean_absolute_error: 0.1373 - val_loss: 11.0545 - val_mean_absolute_error: 2.6019
Epoch 893/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0734 - mean_absolute_error: 0.1095 - val_loss: 11.1757 - val_mean_absolute_error: 2.6073
Epoch 894/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0761 - mean_absolute_error: 0.1138 - val_loss: 11.3148 - val_mean_absolute_error: 2.6099
Epoch 895/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0738 - mean_absolute_error: 0.1056 - val_loss: 11.2091 - val_mean_absolute_error: 2.6190
Epoch 896/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0814 - mean_absolute_error: 0.1165 - val_loss: 11.2372 - val_mean_absolute_error: 2.6121
Epoch 897/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0739 - mean_absolute_error: 0.1089 - val_loss: 11.2523 - val_mean_absolute_error: 2.6124
Epoch 898/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0811 - mean_absolute_error: 0.1200 - val_loss: 11.2460 - val_mean_absolute_error: 2.6144
Epoch 899/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0871 - mean_absolute_error: 0.1334 - val_loss: 11.1357 - val_mean_absolute_error: 2.6105
Epoch 900/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0774 - mean_absolute_error: 0.1242 - val_loss: 11.1862 - val_mean_absolute_error: 2.6075
Epoch 901/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0744 - mean_absolute_error: 0.1220 - val_loss: 11.2842 - val_mean_absolute_error: 2.6405
Epoch 902/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0744 - mean_absolute_error: 0.1208 - val_loss: 11.1749 - val_mean_absolute_error: 2.6047
Epoch 903/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0930 - mean_absolute_error: 0.1314 - val_loss: 11.0562 - val_mean_absolute_error: 2.5937
Epoch 904/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0795 - mean_absolute_error: 0.1224 - val_loss: 11.3656 - val_mean_absolute_error: 2.6297
Epoch 905/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0928 - mean_absolute_error: 0.1243 - val_loss: 11.0786 - val_mean_absolute_error: 2.6372
Epoch 906/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1055 - mean_absolute_error: 0.1483 - val_loss: 11.1037 - val_mean_absolute_error: 2.6017
Epoch 907/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0835 - mean_absolute_error: 0.1214 - val_loss: 11.1164 - val_mean_absolute_error: 2.6098
Epoch 908/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1406 - mean_absolute_error: 0.1361 - val_loss: 11.3302 - val_mean_absolute_error: 2.6316
Epoch 909/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2578 - mean_absolute_error: 0.2525 - val_loss: 11.4789 - val_mean_absolute_error: 2.5833
Epoch 910/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4509 - mean_absolute_error: 0.3220 - val_loss: 10.9792 - val_mean_absolute_error: 2.6170
Epoch 911/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2597 - mean_absolute_error: 0.3257 - val_loss: 11.0506 - val_mean_absolute_error: 2.6042
Epoch 912/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2450 - mean_absolute_error: 0.3295 - val_loss: 11.4915 - val_mean_absolute_error: 2.6332
Epoch 913/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1820 - mean_absolute_error: 0.2833 - val_loss: 11.3997 - val_mean_absolute_error: 2.6809
Epoch 914/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1238 - mean_absolute_error: 0.2278 - val_loss: 11.1969 - val_mean_absolute_error: 2.6148
Epoch 915/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1339 - mean_absolute_error: 0.2142 - val_loss: 11.0669 - val_mean_absolute_error: 2.6243
Epoch 916/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1032 - mean_absolute_error: 0.1881 - val_loss: 11.3040 - val_mean_absolute_error: 2.6372
Epoch 917/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1055 - mean_absolute_error: 0.1708 - val_loss: 11.1392 - val_mean_absolute_error: 2.6269
Epoch 918/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0925 - mean_absolute_error: 0.1585 - val_loss: 11.3230 - val_mean_absolute_error: 2.6365
Epoch 919/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0900 - mean_absolute_error: 0.1434 - val_loss: 10.9745 - val_mean_absolute_error: 2.5956
Epoch 920/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0807 - mean_absolute_error: 0.1370 - val_loss: 11.1464 - val_mean_absolute_error: 2.6050
Epoch 921/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0860 - mean_absolute_error: 0.1394 - val_loss: 11.3811 - val_mean_absolute_error: 2.6818
Epoch 922/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0836 - mean_absolute_error: 0.1403 - val_loss: 11.2548 - val_mean_absolute_error: 2.6212
Epoch 923/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0776 - mean_absolute_error: 0.1223 - val_loss: 11.2110 - val_mean_absolute_error: 2.6217
Epoch 924/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0716 - mean_absolute_error: 0.1184 - val_loss: 11.2845 - val_mean_absolute_error: 2.6146
Epoch 925/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.0745 - mean_absolute_error: 0.1112 - val_loss: 11.0930 - val_mean_absolute_error: 2.6055
Epoch 926/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0758 - mean_absolute_error: 0.1112 - val_loss: 11.0257 - val_mean_absolute_error: 2.6016
Epoch 927/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0765 - mean_absolute_error: 0.1195 - val_loss: 11.2188 - val_mean_absolute_error: 2.6421
Epoch 928/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0726 - mean_absolute_error: 0.1164 - val_loss: 11.2188 - val_mean_absolute_error: 2.6000
Epoch 929/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0803 - mean_absolute_error: 0.1230 - val_loss: 10.9848 - val_mean_absolute_error: 2.5988
Epoch 930/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0761 - mean_absolute_error: 0.1374 - val_loss: 11.3888 - val_mean_absolute_error: 2.6543
Epoch 931/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.0784 - mean_absolute_error: 0.1359 - val_loss: 11.0000 - val_mean_absolute_error: 2.5834
Epoch 932/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0752 - mean_absolute_error: 0.1266 - val_loss: 11.0095 - val_mean_absolute_error: 2.5907
Epoch 933/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0773 - mean_absolute_error: 0.1205 - val_loss: 11.2841 - val_mean_absolute_error: 2.6455
Epoch 934/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0804 - mean_absolute_error: 0.1332 - val_loss: 11.0779 - val_mean_absolute_error: 2.6012
Epoch 935/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0739 - mean_absolute_error: 0.1220 - val_loss: 11.2427 - val_mean_absolute_error: 2.6035
Epoch 936/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0766 - mean_absolute_error: 0.1225 - val_loss: 11.1223 - val_mean_absolute_error: 2.6075
Epoch 937/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0741 - mean_absolute_error: 0.1126 - val_loss: 11.0944 - val_mean_absolute_error: 2.5910
Epoch 938/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0807 - mean_absolute_error: 0.1223 - val_loss: 11.1461 - val_mean_absolute_error: 2.6583
Epoch 939/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0896 - mean_absolute_error: 0.1395 - val_loss: 11.2037 - val_mean_absolute_error: 2.6040
Epoch 940/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0769 - mean_absolute_error: 0.1361 - val_loss: 11.1988 - val_mean_absolute_error: 2.6428
Epoch 941/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0829 - mean_absolute_error: 0.1308 - val_loss: 11.1132 - val_mean_absolute_error: 2.6004
Epoch 942/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0810 - mean_absolute_error: 0.1364 - val_loss: 11.1591 - val_mean_absolute_error: 2.6246
Epoch 943/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0764 - mean_absolute_error: 0.1277 - val_loss: 11.1029 - val_mean_absolute_error: 2.6043
Epoch 944/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0805 - mean_absolute_error: 0.1233 - val_loss: 11.3876 - val_mean_absolute_error: 2.6474
Epoch 945/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0832 - mean_absolute_error: 0.1300 - val_loss: 11.2524 - val_mean_absolute_error: 2.6385
Epoch 946/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0745 - mean_absolute_error: 0.1166 - val_loss: 11.3848 - val_mean_absolute_error: 2.6341
Epoch 947/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0755 - mean_absolute_error: 0.1360 - val_loss: 11.1582 - val_mean_absolute_error: 2.6179
Epoch 948/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0919 - mean_absolute_error: 0.1621 - val_loss: 11.2005 - val_mean_absolute_error: 2.6473
Epoch 949/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0779 - mean_absolute_error: 0.1376 - val_loss: 11.2634 - val_mean_absolute_error: 2.6352
Epoch 950/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0826 - mean_absolute_error: 0.1283 - val_loss: 11.2864 - val_mean_absolute_error: 2.6480
Epoch 951/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0689 - mean_absolute_error: 0.1112 - val_loss: 11.1598 - val_mean_absolute_error: 2.6091
Epoch 952/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0766 - mean_absolute_error: 0.1116 - val_loss: 11.1621 - val_mean_absolute_error: 2.6049
Epoch 953/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0835 - mean_absolute_error: 0.1131 - val_loss: 11.2149 - val_mean_absolute_error: 2.6408
Epoch 954/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0802 - mean_absolute_error: 0.1219 - val_loss: 11.3457 - val_mean_absolute_error: 2.6284
Epoch 955/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0767 - mean_absolute_error: 0.1274 - val_loss: 11.2310 - val_mean_absolute_error: 2.6326
Epoch 956/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0819 - mean_absolute_error: 0.1296 - val_loss: 11.3314 - val_mean_absolute_error: 2.6229
Epoch 957/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0826 - mean_absolute_error: 0.1464 - val_loss: 11.1599 - val_mean_absolute_error: 2.6377
Epoch 958/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1286 - mean_absolute_error: 0.1604 - val_loss: 11.4124 - val_mean_absolute_error: 2.6480
Epoch 959/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0988 - mean_absolute_error: 0.1637 - val_loss: 11.3020 - val_mean_absolute_error: 2.6392
Epoch 960/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1084 - mean_absolute_error: 0.1784 - val_loss: 11.3176 - val_mean_absolute_error: 2.6482
Epoch 961/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0935 - mean_absolute_error: 0.1571 - val_loss: 10.8776 - val_mean_absolute_error: 2.5747
Epoch 962/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0887 - mean_absolute_error: 0.1643 - val_loss: 11.2303 - val_mean_absolute_error: 2.6250
Epoch 963/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1029 - mean_absolute_error: 0.1757 - val_loss: 11.4656 - val_mean_absolute_error: 2.6849
Epoch 964/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1079 - mean_absolute_error: 0.1830 - val_loss: 11.3713 - val_mean_absolute_error: 2.6392
Epoch 965/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1099 - mean_absolute_error: 0.1803 - val_loss: 11.3628 - val_mean_absolute_error: 2.6523
Epoch 966/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0991 - mean_absolute_error: 0.1492 - val_loss: 11.3513 - val_mean_absolute_error: 2.6026
Epoch 967/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1000 - mean_absolute_error: 0.1582 - val_loss: 11.1102 - val_mean_absolute_error: 2.6069
Epoch 968/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0837 - mean_absolute_error: 0.1507 - val_loss: 11.4430 - val_mean_absolute_error: 2.6802
Epoch 969/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0924 - mean_absolute_error: 0.1748 - val_loss: 11.2165 - val_mean_absolute_error: 2.6277
Epoch 970/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0767 - mean_absolute_error: 0.1229 - val_loss: 11.2033 - val_mean_absolute_error: 2.6344
Epoch 971/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0755 - mean_absolute_error: 0.1275 - val_loss: 11.2295 - val_mean_absolute_error: 2.6198
Epoch 972/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0965 - mean_absolute_error: 0.1513 - val_loss: 11.1237 - val_mean_absolute_error: 2.6411
Epoch 973/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0994 - mean_absolute_error: 0.1739 - val_loss: 11.3036 - val_mean_absolute_error: 2.6321
Epoch 974/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0961 - mean_absolute_error: 0.1747 - val_loss: 11.3091 - val_mean_absolute_error: 2.6691
Epoch 975/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1007 - mean_absolute_error: 0.1756 - val_loss: 11.2611 - val_mean_absolute_error: 2.6438
Epoch 976/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0854 - mean_absolute_error: 0.1507 - val_loss: 11.4312 - val_mean_absolute_error: 2.6313
Epoch 977/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0806 - mean_absolute_error: 0.1302 - val_loss: 11.2457 - val_mean_absolute_error: 2.6620
Epoch 978/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0756 - mean_absolute_error: 0.1271 - val_loss: 11.1416 - val_mean_absolute_error: 2.6216
Epoch 979/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0742 - mean_absolute_error: 0.1299 - val_loss: 11.4672 - val_mean_absolute_error: 2.6892
Epoch 980/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0878 - mean_absolute_error: 0.1358 - val_loss: 11.3912 - val_mean_absolute_error: 2.6469
Epoch 981/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.1158 - mean_absolute_error: 0.1777 - val_loss: 11.0629 - val_mean_absolute_error: 2.6128
Epoch 982/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2313 - mean_absolute_error: 0.2780 - val_loss: 11.1152 - val_mean_absolute_error: 2.6529
Epoch 983/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1563 - mean_absolute_error: 0.2394 - val_loss: 11.3794 - val_mean_absolute_error: 2.6305
Epoch 984/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1094 - mean_absolute_error: 0.2046 - val_loss: 11.2741 - val_mean_absolute_error: 2.6715
Epoch 985/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1125 - mean_absolute_error: 0.1864 - val_loss: 11.2821 - val_mean_absolute_error: 2.6111
Epoch 986/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0943 - mean_absolute_error: 0.1693 - val_loss: 10.8967 - val_mean_absolute_error: 2.6015
Epoch 987/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0978 - mean_absolute_error: 0.1691 - val_loss: 11.0920 - val_mean_absolute_error: 2.6258
Epoch 988/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0845 - mean_absolute_error: 0.1451 - val_loss: 11.1667 - val_mean_absolute_error: 2.6404
Epoch 989/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0961 - mean_absolute_error: 0.1470 - val_loss: 11.4085 - val_mean_absolute_error: 2.6475
Epoch 990/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0919 - mean_absolute_error: 0.1648 - val_loss: 10.9679 - val_mean_absolute_error: 2.6030
Epoch 991/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0794 - mean_absolute_error: 0.1384 - val_loss: 11.2004 - val_mean_absolute_error: 2.6120
Epoch 992/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0708 - mean_absolute_error: 0.1148 - val_loss: 11.1887 - val_mean_absolute_error: 2.6321
Epoch 993/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0765 - mean_absolute_error: 0.1156 - val_loss: 11.0180 - val_mean_absolute_error: 2.6060
Epoch 994/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0694 - mean_absolute_error: 0.0979 - val_loss: 11.0212 - val_mean_absolute_error: 2.6018
Epoch 995/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0758 - mean_absolute_error: 0.1016 - val_loss: 11.1175 - val_mean_absolute_error: 2.6165
Epoch 996/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0781 - mean_absolute_error: 0.1133 - val_loss: 11.2101 - val_mean_absolute_error: 2.6485
Epoch 997/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1017 - mean_absolute_error: 0.1453 - val_loss: 11.2507 - val_mean_absolute_error: 2.6030
Epoch 998/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.0993 - mean_absolute_error: 0.1555 - val_loss: 11.2464 - val_mean_absolute_error: 2.6698
Epoch 999/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1071 - mean_absolute_error: 0.1682 - val_loss: 11.3444 - val_mean_absolute_error: 2.6537
Epoch 1000/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1121 - mean_absolute_error: 0.1817 - val_loss: 11.3232 - val_mean_absolute_error: 2.6454
7/7 [==============================] - 1s 5ms/step
1/1 [==============================] - 0s 19ms/step
1/1 [==============================] - 0s 27ms/step

# Calculate the RMSE
rmse_lstm = sqrt(mean_squared_error(y_test_BAC, test_predictions_BAC))
print('The RMSE value of LSTM model (BAC): {:.4f}'.format(rmse_lstm))

The RMSE value of LSTM model (BAC): 1.8953

# Plot Training Observations VS Training Predictions 
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_train_BAC, train_predictions_BAC)
plt.plot(dates_train_BAC, y_train_BAC)
plt.title('LSTM: Training Actual Returns/Training Predicted Returns (BAC)', fontsize=16)
plt.legend(['BAC Training Predictions', 'BAC Training Observations'])

# Plot Testing Observations VS Testing Predictions 
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_test_BAC, test_predictions_BAC)
plt.plot(dates_test_BAC, y_test_BAC)
plt.title('LSTM: Testing Actual Returns/Testing Predicted Returns (BAC)', fontsize=16)
plt.legend(['BAC Testing Predictions', 'BAC Testing Observations'])

# General Plot (Training, Validation & testing)
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_train_BAC, train_predictions_BAC)
plt.plot(dates_train_BAC, y_train_BAC)
plt.plot(dates_val_BAC, val_predictions_BAC)
plt.plot(dates_val_BAC, y_val_BAC)
plt.plot(dates_test_BAC, test_predictions_BAC)
plt.plot(dates_test_BAC, y_test_BAC)
plt.title('LSTM: General forecasting plot (BAC)', fontsize=16)
plt.legend(['BAC Training Predictions', 
            'BAC Training Observations',
            'BAC Validation Predictions', 
            'BAC Validation Observations',
            'BAC Testing Predictions', 
            'BAC Testing Observations'])

<matplotlib.legend.Legend at 0x7fa8c1445b80>

BMW

# transform a time series dataset into a supervised learning dataset (Input : Output)
def BMW_to_windowed_BMW(BMW_RET, first_date_str, last_date_str, n=3):
    first_date = str_to_datetime(first_date_str)
    last_date  = str_to_datetime(last_date_str)
    
    target_date = first_date
    
    dates_BMW = []
    X, Y = [], []
    
    last_time = False
    while True:
        BMW_subset = BMW_RET.loc[:target_date].tail(n+1)
        
        if len(BMW_subset) != n+1:
            print(f'Error: Window of size {n} is too large for date {target_date}')
            return
        
        values = BMW_subset['Ret_BMW'].to_numpy()
        x, y = values[:-1], values[-1]
        
        dates_BMW.append(target_date)
        X.append(x)
        Y.append(y)
        
        next_week = BMW_RET.loc[target_date:target_date+datetime.timedelta(days=7)]
        next_datetime_str = str(next_week.head(2).tail(1).index.values[0])
        next_date_str = next_datetime_str.split('T')[0]
        year_month_day = next_date_str.split('-')
        year, month, day = year_month_day
        next_date = datetime.datetime(day=int(day), month=int(month), year=int(year))
        
        if last_time:
            break
        
        target_date = next_date
        
        if target_date == last_date:
            last_time = True
    ret_BMW = pd.DataFrame({})
    ret_BMW['Target Date'] = dates_BMW
    
    X = np.array(X)
    for i in range(0, n):
        X[:, i]
        ret_BMW[f'Target-{n-i}'] = X[:, i]
        
    ret_BMW['Target'] = Y
    
    return ret_BMW

# Start day second time around: '2020-01-03'
windowed_BMW = BMW_to_windowed_BMW(BMW_RET, 
                                '2020-01-03', 
                                '2020-12-30', 
                                n=3)

# Convert our new dataset into numpy arrays (to feed it directly into a tensorflow model)
def windowed_BMW_to_date_X_y(windowed_dataframe):
    BMW_as_np = windowed_dataframe.to_numpy()
    
    dates_BMW = BMW_as_np[:, 0] 
    
    middle_matrix_BMW = BMW_as_np[:, 1:-1]
    X_BMW = middle_matrix_BMW.reshape((len(dates_BMW), middle_matrix_BMW.shape[1], 1))
    
    Y_BMW = BMW_as_np[:, -1]
    
    return dates_BMW, X_BMW.astype(np.float32), Y_BMW.astype(np.float32)

dates_BMW, X_BMW, y_BMW = windowed_BMW_to_date_X_y(windowed_BMW)

# Split the data into training, validation and testing partitions 
q_85_BMW = int(len(dates_BMW) * .85)
q_95_BMW = int(len(dates_BMW) * .95)

dates_train_BMW, X_train_BMW, y_train_BMW = dates_BMW[:q_85_BMW], X_BMW[:q_85_BMW], y_BMW[:q_85_BMW]
dates_val_BMW, X_val_BMW, y_val_BMW = dates_BMW[q_85_BMW:q_95_BMW], X_BMW[q_85_BMW:q_95_BMW], y_BMW[q_85_BMW:q_95_BMW]
dates_test_BMW, X_test_BMW, y_test_BMW = dates_BMW[q_95_BMW:], X_BMW[q_95_BMW:], y_BMW[q_95_BMW:]

# Create & train the LSTM model 
model_BMW = Sequential([layers.Input((3, 1)),
                    layers.LSTM(264),
                    layers.Dense(132, activation='relu'),
                    layers.Dense(132, activation='relu'),
                    layers.Dense(1)])

model_BMW.compile(loss='mse', 
              optimizer=Adam(learning_rate=0.001),
              metrics=['mean_absolute_error'])

# Fitting the LSTM model 
model_BMW.fit(X_train_BMW, y_train_BMW, validation_data=(X_val_BMW, y_val_BMW), epochs=1000)

# Forecasting
train_predictions_BMW = model_BMW.predict(X_train_BMW).flatten()
val_predictions_BMW = model_BMW.predict(X_val_BMW).flatten()
test_predictions_BMW = model_BMW.predict(X_test_BMW).flatten()

Epoch 1/1000
7/7 [==============================] - 3s 110ms/step - loss: 9.2244 - mean_absolute_error: 2.0078 - val_loss: 4.1963 - val_mean_absolute_error: 1.4144
Epoch 2/1000
7/7 [==============================] - 0s 30ms/step - loss: 9.1848 - mean_absolute_error: 2.0069 - val_loss: 4.4034 - val_mean_absolute_error: 1.4704
Epoch 3/1000
7/7 [==============================] - 0s 25ms/step - loss: 9.1018 - mean_absolute_error: 1.9936 - val_loss: 4.4094 - val_mean_absolute_error: 1.4801
Epoch 4/1000
7/7 [==============================] - 0s 25ms/step - loss: 9.0437 - mean_absolute_error: 1.9896 - val_loss: 4.3704 - val_mean_absolute_error: 1.4788
Epoch 5/1000
7/7 [==============================] - 0s 22ms/step - loss: 8.9346 - mean_absolute_error: 1.9820 - val_loss: 4.3977 - val_mean_absolute_error: 1.4899
Epoch 6/1000
7/7 [==============================] - 0s 23ms/step - loss: 8.8733 - mean_absolute_error: 1.9855 - val_loss: 4.5701 - val_mean_absolute_error: 1.5347
Epoch 7/1000
7/7 [==============================] - 0s 26ms/step - loss: 8.8471 - mean_absolute_error: 1.9936 - val_loss: 4.7628 - val_mean_absolute_error: 1.5747
Epoch 8/1000
7/7 [==============================] - 0s 27ms/step - loss: 8.6824 - mean_absolute_error: 1.9830 - val_loss: 4.8329 - val_mean_absolute_error: 1.5916
Epoch 9/1000
7/7 [==============================] - 0s 26ms/step - loss: 8.5197 - mean_absolute_error: 1.9621 - val_loss: 4.8599 - val_mean_absolute_error: 1.6162
Epoch 10/1000
7/7 [==============================] - 0s 21ms/step - loss: 8.3572 - mean_absolute_error: 1.9550 - val_loss: 4.4562 - val_mean_absolute_error: 1.5505
Epoch 11/1000
7/7 [==============================] - 0s 25ms/step - loss: 8.1227 - mean_absolute_error: 1.9331 - val_loss: 5.5949 - val_mean_absolute_error: 1.7538
Epoch 12/1000
7/7 [==============================] - 0s 24ms/step - loss: 7.8975 - mean_absolute_error: 1.9203 - val_loss: 5.2890 - val_mean_absolute_error: 1.7185
Epoch 13/1000
7/7 [==============================] - 0s 22ms/step - loss: 7.5778 - mean_absolute_error: 1.9250 - val_loss: 4.8628 - val_mean_absolute_error: 1.6621
Epoch 14/1000
7/7 [==============================] - 0s 24ms/step - loss: 7.1852 - mean_absolute_error: 1.8807 - val_loss: 4.4441 - val_mean_absolute_error: 1.6009
Epoch 15/1000
7/7 [==============================] - 0s 29ms/step - loss: 7.0847 - mean_absolute_error: 1.8664 - val_loss: 5.8303 - val_mean_absolute_error: 1.8077
Epoch 16/1000
7/7 [==============================] - 0s 26ms/step - loss: 6.9079 - mean_absolute_error: 1.8417 - val_loss: 5.8020 - val_mean_absolute_error: 1.7910
Epoch 17/1000
7/7 [==============================] - 0s 27ms/step - loss: 6.7662 - mean_absolute_error: 1.7933 - val_loss: 4.9335 - val_mean_absolute_error: 1.6636
Epoch 18/1000
7/7 [==============================] - 0s 27ms/step - loss: 6.4134 - mean_absolute_error: 1.8019 - val_loss: 4.9147 - val_mean_absolute_error: 1.6698
Epoch 19/1000
7/7 [==============================] - 0s 26ms/step - loss: 6.2398 - mean_absolute_error: 1.8193 - val_loss: 5.5441 - val_mean_absolute_error: 1.7807
Epoch 20/1000
7/7 [==============================] - 0s 32ms/step - loss: 6.0101 - mean_absolute_error: 1.7651 - val_loss: 6.2547 - val_mean_absolute_error: 1.8864
Epoch 21/1000
7/7 [==============================] - 0s 21ms/step - loss: 6.0010 - mean_absolute_error: 1.7512 - val_loss: 5.0777 - val_mean_absolute_error: 1.6812
Epoch 22/1000
7/7 [==============================] - 0s 23ms/step - loss: 5.8023 - mean_absolute_error: 1.7375 - val_loss: 4.8112 - val_mean_absolute_error: 1.6322
Epoch 23/1000
7/7 [==============================] - 0s 22ms/step - loss: 5.8751 - mean_absolute_error: 1.7298 - val_loss: 4.4381 - val_mean_absolute_error: 1.5401
Epoch 24/1000
7/7 [==============================] - 0s 32ms/step - loss: 8.0805 - mean_absolute_error: 1.9160 - val_loss: 4.8904 - val_mean_absolute_error: 1.6353
Epoch 25/1000
7/7 [==============================] - 0s 27ms/step - loss: 6.0141 - mean_absolute_error: 1.7438 - val_loss: 5.4825 - val_mean_absolute_error: 1.7460
Epoch 26/1000
7/7 [==============================] - 0s 24ms/step - loss: 6.0345 - mean_absolute_error: 1.7679 - val_loss: 4.6707 - val_mean_absolute_error: 1.6196
Epoch 27/1000
7/7 [==============================] - 0s 28ms/step - loss: 5.8384 - mean_absolute_error: 1.7263 - val_loss: 4.1634 - val_mean_absolute_error: 1.5174
Epoch 28/1000
7/7 [==============================] - 0s 27ms/step - loss: 5.6189 - mean_absolute_error: 1.6890 - val_loss: 6.0335 - val_mean_absolute_error: 1.8429
Epoch 29/1000
7/7 [==============================] - 0s 24ms/step - loss: 5.6530 - mean_absolute_error: 1.7148 - val_loss: 5.2906 - val_mean_absolute_error: 1.7188
Epoch 30/1000
7/7 [==============================] - 0s 22ms/step - loss: 5.6147 - mean_absolute_error: 1.6890 - val_loss: 4.1774 - val_mean_absolute_error: 1.5439
Epoch 31/1000
7/7 [==============================] - 0s 27ms/step - loss: 5.4768 - mean_absolute_error: 1.6639 - val_loss: 5.4316 - val_mean_absolute_error: 1.7537
Epoch 32/1000
7/7 [==============================] - 0s 25ms/step - loss: 5.2931 - mean_absolute_error: 1.6515 - val_loss: 5.2774 - val_mean_absolute_error: 1.7227
Epoch 33/1000
7/7 [==============================] - 0s 26ms/step - loss: 5.1996 - mean_absolute_error: 1.6262 - val_loss: 4.9823 - val_mean_absolute_error: 1.6795
Epoch 34/1000
7/7 [==============================] - 0s 25ms/step - loss: 5.2868 - mean_absolute_error: 1.6447 - val_loss: 5.0298 - val_mean_absolute_error: 1.6891
Epoch 35/1000
7/7 [==============================] - 0s 28ms/step - loss: 5.0828 - mean_absolute_error: 1.6188 - val_loss: 5.9036 - val_mean_absolute_error: 1.8282
Epoch 36/1000
7/7 [==============================] - 0s 25ms/step - loss: 5.0931 - mean_absolute_error: 1.6189 - val_loss: 4.9521 - val_mean_absolute_error: 1.6838
Epoch 37/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.9963 - mean_absolute_error: 1.5782 - val_loss: 5.2415 - val_mean_absolute_error: 1.7157
Epoch 38/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.0815 - mean_absolute_error: 1.6153 - val_loss: 6.5121 - val_mean_absolute_error: 1.9137
Epoch 39/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.8654 - mean_absolute_error: 1.5745 - val_loss: 4.1035 - val_mean_absolute_error: 1.5189
Epoch 40/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.0575 - mean_absolute_error: 1.5894 - val_loss: 4.5927 - val_mean_absolute_error: 1.5969
Epoch 41/1000
7/7 [==============================] - 0s 26ms/step - loss: 4.8597 - mean_absolute_error: 1.5776 - val_loss: 5.9205 - val_mean_absolute_error: 1.8128
Epoch 42/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.9186 - mean_absolute_error: 1.5913 - val_loss: 6.0286 - val_mean_absolute_error: 1.8370
Epoch 43/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.9361 - mean_absolute_error: 1.5694 - val_loss: 4.7951 - val_mean_absolute_error: 1.6370
Epoch 44/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.7974 - mean_absolute_error: 1.5616 - val_loss: 5.8447 - val_mean_absolute_error: 1.8385
Epoch 45/1000
7/7 [==============================] - 0s 26ms/step - loss: 4.8634 - mean_absolute_error: 1.5593 - val_loss: 5.8015 - val_mean_absolute_error: 1.8108
Epoch 46/1000
7/7 [==============================] - 0s 21ms/step - loss: 4.7249 - mean_absolute_error: 1.5864 - val_loss: 6.8052 - val_mean_absolute_error: 1.9833
Epoch 47/1000
7/7 [==============================] - 0s 21ms/step - loss: 4.7156 - mean_absolute_error: 1.5631 - val_loss: 5.1090 - val_mean_absolute_error: 1.6742
Epoch 48/1000
7/7 [==============================] - 0s 23ms/step - loss: 4.6874 - mean_absolute_error: 1.5586 - val_loss: 5.8968 - val_mean_absolute_error: 1.8164
Epoch 49/1000
7/7 [==============================] - 0s 22ms/step - loss: 4.5835 - mean_absolute_error: 1.5399 - val_loss: 4.6425 - val_mean_absolute_error: 1.6284
Epoch 50/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.8136 - mean_absolute_error: 1.5827 - val_loss: 5.1649 - val_mean_absolute_error: 1.6951
Epoch 51/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.6280 - mean_absolute_error: 1.5712 - val_loss: 6.0887 - val_mean_absolute_error: 1.8506
Epoch 52/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.6440 - mean_absolute_error: 1.5770 - val_loss: 5.4791 - val_mean_absolute_error: 1.7504
Epoch 53/1000
7/7 [==============================] - 0s 24ms/step - loss: 5.3037 - mean_absolute_error: 1.6391 - val_loss: 5.5614 - val_mean_absolute_error: 1.7565
Epoch 54/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.9740 - mean_absolute_error: 1.6481 - val_loss: 6.0916 - val_mean_absolute_error: 1.8357
Epoch 55/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.8725 - mean_absolute_error: 1.6068 - val_loss: 5.1977 - val_mean_absolute_error: 1.7098
Epoch 56/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.0443 - mean_absolute_error: 1.6062 - val_loss: 5.6040 - val_mean_absolute_error: 1.7448
Epoch 57/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.7368 - mean_absolute_error: 1.6016 - val_loss: 5.9243 - val_mean_absolute_error: 1.7774
Epoch 58/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.4323 - mean_absolute_error: 1.5220 - val_loss: 5.3792 - val_mean_absolute_error: 1.7120
Epoch 59/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.4676 - mean_absolute_error: 1.5208 - val_loss: 6.0015 - val_mean_absolute_error: 1.8181
Epoch 60/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.4306 - mean_absolute_error: 1.5113 - val_loss: 6.4825 - val_mean_absolute_error: 1.8735
Epoch 61/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.3093 - mean_absolute_error: 1.4895 - val_loss: 5.2506 - val_mean_absolute_error: 1.7042
Epoch 62/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.2495 - mean_absolute_error: 1.4764 - val_loss: 5.8570 - val_mean_absolute_error: 1.7972
Epoch 63/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.2338 - mean_absolute_error: 1.4802 - val_loss: 5.8019 - val_mean_absolute_error: 1.7788
Epoch 64/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.1490 - mean_absolute_error: 1.4631 - val_loss: 5.9618 - val_mean_absolute_error: 1.7934
Epoch 65/1000
7/7 [==============================] - 0s 30ms/step - loss: 4.1620 - mean_absolute_error: 1.4582 - val_loss: 6.4314 - val_mean_absolute_error: 1.8871
Epoch 66/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.2845 - mean_absolute_error: 1.4913 - val_loss: 5.3353 - val_mean_absolute_error: 1.6316
Epoch 67/1000
7/7 [==============================] - 0s 17ms/step - loss: 4.1063 - mean_absolute_error: 1.4659 - val_loss: 6.9942 - val_mean_absolute_error: 1.9452
Epoch 68/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.1593 - mean_absolute_error: 1.4784 - val_loss: 6.6622 - val_mean_absolute_error: 1.9369
Epoch 69/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.2263 - mean_absolute_error: 1.4912 - val_loss: 5.0431 - val_mean_absolute_error: 1.5899
Epoch 70/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.0303 - mean_absolute_error: 1.4863 - val_loss: 7.0934 - val_mean_absolute_error: 1.9309
Epoch 71/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.9364 - mean_absolute_error: 1.4319 - val_loss: 5.6681 - val_mean_absolute_error: 1.7565
Epoch 72/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.9806 - mean_absolute_error: 1.4477 - val_loss: 6.6652 - val_mean_absolute_error: 1.8979
Epoch 73/1000
7/7 [==============================] - 0s 23ms/step - loss: 4.0739 - mean_absolute_error: 1.4778 - val_loss: 6.6826 - val_mean_absolute_error: 1.8833
Epoch 74/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.8507 - mean_absolute_error: 1.4290 - val_loss: 5.6335 - val_mean_absolute_error: 1.7471
Epoch 75/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.9241 - mean_absolute_error: 1.4522 - val_loss: 7.3716 - val_mean_absolute_error: 1.9865
Epoch 76/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.1223 - mean_absolute_error: 1.4920 - val_loss: 6.4916 - val_mean_absolute_error: 1.8313
Epoch 77/1000
7/7 [==============================] - 0s 21ms/step - loss: 4.3310 - mean_absolute_error: 1.5176 - val_loss: 4.6770 - val_mean_absolute_error: 1.5725
Epoch 78/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.1479 - mean_absolute_error: 1.4904 - val_loss: 8.4678 - val_mean_absolute_error: 2.1453
Epoch 79/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.0095 - mean_absolute_error: 1.4836 - val_loss: 4.8887 - val_mean_absolute_error: 1.6679
Epoch 80/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.0462 - mean_absolute_error: 1.4564 - val_loss: 5.7196 - val_mean_absolute_error: 1.7961
Epoch 81/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.9921 - mean_absolute_error: 1.4673 - val_loss: 6.8410 - val_mean_absolute_error: 1.9473
Epoch 82/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.8732 - mean_absolute_error: 1.4533 - val_loss: 5.4718 - val_mean_absolute_error: 1.7294
Epoch 83/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.1376 - mean_absolute_error: 1.4636 - val_loss: 6.6659 - val_mean_absolute_error: 1.8857
Epoch 84/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.6940 - mean_absolute_error: 1.4020 - val_loss: 6.0998 - val_mean_absolute_error: 1.7976
Epoch 85/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.9258 - mean_absolute_error: 1.4386 - val_loss: 7.0033 - val_mean_absolute_error: 1.9748
Epoch 86/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.4058 - mean_absolute_error: 1.5428 - val_loss: 5.6848 - val_mean_absolute_error: 1.7032
Epoch 87/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.8271 - mean_absolute_error: 1.4313 - val_loss: 6.9041 - val_mean_absolute_error: 1.9195
Epoch 88/1000
7/7 [==============================] - 0s 28ms/step - loss: 4.0342 - mean_absolute_error: 1.4582 - val_loss: 6.9867 - val_mean_absolute_error: 1.9118
Epoch 89/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.6355 - mean_absolute_error: 1.3923 - val_loss: 5.8786 - val_mean_absolute_error: 1.7217
Epoch 90/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.7730 - mean_absolute_error: 1.4221 - val_loss: 7.4170 - val_mean_absolute_error: 2.0006
Epoch 91/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.7654 - mean_absolute_error: 1.4263 - val_loss: 7.1070 - val_mean_absolute_error: 1.9660
Epoch 92/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.7027 - mean_absolute_error: 1.3999 - val_loss: 6.4420 - val_mean_absolute_error: 1.8461
Epoch 93/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.3975 - mean_absolute_error: 1.3589 - val_loss: 7.3641 - val_mean_absolute_error: 1.9317
Epoch 94/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.4035 - mean_absolute_error: 1.3558 - val_loss: 6.5203 - val_mean_absolute_error: 1.8514
Epoch 95/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.2940 - mean_absolute_error: 1.3126 - val_loss: 6.9403 - val_mean_absolute_error: 1.9203
Epoch 96/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.1839 - mean_absolute_error: 1.2898 - val_loss: 7.3520 - val_mean_absolute_error: 1.9076
Epoch 97/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.3088 - mean_absolute_error: 1.3393 - val_loss: 7.3261 - val_mean_absolute_error: 1.8839
Epoch 98/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.4045 - mean_absolute_error: 1.3496 - val_loss: 6.7062 - val_mean_absolute_error: 1.8985
Epoch 99/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.0813 - mean_absolute_error: 1.2974 - val_loss: 8.5337 - val_mean_absolute_error: 2.0491
Epoch 100/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.0747 - mean_absolute_error: 1.2792 - val_loss: 6.1616 - val_mean_absolute_error: 1.7792
Epoch 101/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.2975 - mean_absolute_error: 1.3256 - val_loss: 8.6968 - val_mean_absolute_error: 2.1249
Epoch 102/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.1137 - mean_absolute_error: 1.2999 - val_loss: 7.4863 - val_mean_absolute_error: 1.9088
Epoch 103/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.9998 - mean_absolute_error: 1.2540 - val_loss: 7.2050 - val_mean_absolute_error: 1.9846
Epoch 104/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.8672 - mean_absolute_error: 1.2218 - val_loss: 8.0776 - val_mean_absolute_error: 2.0574
Epoch 105/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.9359 - mean_absolute_error: 1.2769 - val_loss: 6.2774 - val_mean_absolute_error: 1.8254
Epoch 106/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.8213 - mean_absolute_error: 1.2409 - val_loss: 7.9148 - val_mean_absolute_error: 2.0059
Epoch 107/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.8023 - mean_absolute_error: 1.2400 - val_loss: 7.0492 - val_mean_absolute_error: 1.9049
Epoch 108/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.7374 - mean_absolute_error: 1.2023 - val_loss: 8.2303 - val_mean_absolute_error: 2.0900
Epoch 109/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.8059 - mean_absolute_error: 1.2422 - val_loss: 7.7433 - val_mean_absolute_error: 2.0203
Epoch 110/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.7419 - mean_absolute_error: 1.2164 - val_loss: 7.6234 - val_mean_absolute_error: 2.0240
Epoch 111/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.7110 - mean_absolute_error: 1.1634 - val_loss: 7.7090 - val_mean_absolute_error: 2.0059
Epoch 112/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.7313 - mean_absolute_error: 1.2108 - val_loss: 8.1664 - val_mean_absolute_error: 2.0268
Epoch 113/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5663 - mean_absolute_error: 1.1485 - val_loss: 7.9036 - val_mean_absolute_error: 2.0170
Epoch 114/1000
7/7 [==============================] - 0s 22ms/step - loss: 2.4266 - mean_absolute_error: 1.0937 - val_loss: 8.4404 - val_mean_absolute_error: 2.0767
Epoch 115/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4255 - mean_absolute_error: 1.0930 - val_loss: 8.1952 - val_mean_absolute_error: 2.0785
Epoch 116/1000
7/7 [==============================] - 0s 36ms/step - loss: 2.4156 - mean_absolute_error: 1.1228 - val_loss: 7.8497 - val_mean_absolute_error: 2.0578
Epoch 117/1000
7/7 [==============================] - 0s 24ms/step - loss: 2.4883 - mean_absolute_error: 1.1447 - val_loss: 8.9549 - val_mean_absolute_error: 2.1396
Epoch 118/1000
7/7 [==============================] - 0s 25ms/step - loss: 2.4818 - mean_absolute_error: 1.1221 - val_loss: 7.0417 - val_mean_absolute_error: 1.9571
Epoch 119/1000
7/7 [==============================] - 0s 26ms/step - loss: 2.4924 - mean_absolute_error: 1.1484 - val_loss: 10.2599 - val_mean_absolute_error: 2.2731
Epoch 120/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.5134 - mean_absolute_error: 1.1397 - val_loss: 7.7537 - val_mean_absolute_error: 2.0460
Epoch 121/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.3422 - mean_absolute_error: 1.1298 - val_loss: 8.2953 - val_mean_absolute_error: 2.0751
Epoch 122/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.1493 - mean_absolute_error: 1.0373 - val_loss: 9.0435 - val_mean_absolute_error: 2.1447
Epoch 123/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.2709 - mean_absolute_error: 1.0660 - val_loss: 7.9002 - val_mean_absolute_error: 2.0890
Epoch 124/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.3297 - mean_absolute_error: 1.1226 - val_loss: 8.4695 - val_mean_absolute_error: 2.0866
Epoch 125/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.1664 - mean_absolute_error: 1.0307 - val_loss: 9.0073 - val_mean_absolute_error: 2.1310
Epoch 126/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.3115 - mean_absolute_error: 1.0961 - val_loss: 10.2172 - val_mean_absolute_error: 2.2567
Epoch 127/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.1088 - mean_absolute_error: 1.0437 - val_loss: 8.0322 - val_mean_absolute_error: 2.1127
Epoch 128/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.0799 - mean_absolute_error: 1.0290 - val_loss: 9.6314 - val_mean_absolute_error: 2.2091
Epoch 129/1000
7/7 [==============================] - 0s 26ms/step - loss: 1.9660 - mean_absolute_error: 1.0084 - val_loss: 8.1147 - val_mean_absolute_error: 2.1954
Epoch 130/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.1008 - mean_absolute_error: 1.0334 - val_loss: 11.0152 - val_mean_absolute_error: 2.3543
Epoch 131/1000
7/7 [==============================] - 0s 17ms/step - loss: 2.1549 - mean_absolute_error: 1.0712 - val_loss: 8.0927 - val_mean_absolute_error: 2.1655
Epoch 132/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.1254 - mean_absolute_error: 1.0532 - val_loss: 9.8075 - val_mean_absolute_error: 2.2189
Epoch 133/1000
7/7 [==============================] - 0s 17ms/step - loss: 1.9383 - mean_absolute_error: 1.0027 - val_loss: 10.0022 - val_mean_absolute_error: 2.2469
Epoch 134/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9506 - mean_absolute_error: 1.0194 - val_loss: 8.8419 - val_mean_absolute_error: 2.1789
Epoch 135/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9032 - mean_absolute_error: 0.9820 - val_loss: 10.4006 - val_mean_absolute_error: 2.2910
Epoch 136/1000
7/7 [==============================] - 0s 17ms/step - loss: 1.8856 - mean_absolute_error: 0.9742 - val_loss: 9.5521 - val_mean_absolute_error: 2.2535
Epoch 137/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.0534 - mean_absolute_error: 1.0133 - val_loss: 8.2896 - val_mean_absolute_error: 2.1740
Epoch 138/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.1622 - mean_absolute_error: 1.0663 - val_loss: 10.9254 - val_mean_absolute_error: 2.3217
Epoch 139/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.2665 - mean_absolute_error: 1.1283 - val_loss: 8.2426 - val_mean_absolute_error: 2.2457
Epoch 140/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.3328 - mean_absolute_error: 1.1204 - val_loss: 11.3268 - val_mean_absolute_error: 2.4048
Epoch 141/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.2784 - mean_absolute_error: 1.1362 - val_loss: 8.1857 - val_mean_absolute_error: 2.2289
Epoch 142/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.3057 - mean_absolute_error: 1.1317 - val_loss: 10.2976 - val_mean_absolute_error: 2.3172
Epoch 143/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9487 - mean_absolute_error: 1.0147 - val_loss: 8.7907 - val_mean_absolute_error: 2.1852
Epoch 144/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9244 - mean_absolute_error: 0.9901 - val_loss: 10.1586 - val_mean_absolute_error: 2.3065
Epoch 145/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.7946 - mean_absolute_error: 0.9608 - val_loss: 9.5445 - val_mean_absolute_error: 2.2234
Epoch 146/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8934 - mean_absolute_error: 1.0105 - val_loss: 10.0270 - val_mean_absolute_error: 2.2697
Epoch 147/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.2636 - mean_absolute_error: 1.0878 - val_loss: 8.6834 - val_mean_absolute_error: 2.1706
Epoch 148/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.1943 - mean_absolute_error: 1.0796 - val_loss: 11.5819 - val_mean_absolute_error: 2.3760
Epoch 149/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.0576 - mean_absolute_error: 1.0972 - val_loss: 7.8778 - val_mean_absolute_error: 2.2666
Epoch 150/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.1612 - mean_absolute_error: 1.1246 - val_loss: 11.3373 - val_mean_absolute_error: 2.2993
Epoch 151/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.8595 - mean_absolute_error: 1.0262 - val_loss: 9.1254 - val_mean_absolute_error: 2.2548
Epoch 152/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8011 - mean_absolute_error: 0.9996 - val_loss: 9.4454 - val_mean_absolute_error: 2.2379
Epoch 153/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.6430 - mean_absolute_error: 0.9240 - val_loss: 10.0740 - val_mean_absolute_error: 2.2188
Epoch 154/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.7741 - mean_absolute_error: 0.9836 - val_loss: 9.1974 - val_mean_absolute_error: 2.2419
Epoch 155/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5947 - mean_absolute_error: 0.9443 - val_loss: 9.3041 - val_mean_absolute_error: 2.2396
Epoch 156/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.7812 - mean_absolute_error: 0.9473 - val_loss: 11.1087 - val_mean_absolute_error: 2.3344
Epoch 157/1000
7/7 [==============================] - 0s 17ms/step - loss: 2.0260 - mean_absolute_error: 1.0999 - val_loss: 8.9386 - val_mean_absolute_error: 2.2971
Epoch 158/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.6627 - mean_absolute_error: 0.9527 - val_loss: 12.0299 - val_mean_absolute_error: 2.4024
Epoch 159/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.6967 - mean_absolute_error: 0.9706 - val_loss: 8.8274 - val_mean_absolute_error: 2.3413
Epoch 160/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.8405 - mean_absolute_error: 1.0013 - val_loss: 14.3685 - val_mean_absolute_error: 2.7107
Epoch 161/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.7643 - mean_absolute_error: 1.0126 - val_loss: 8.5345 - val_mean_absolute_error: 2.2928
Epoch 162/1000
7/7 [==============================] - 0s 30ms/step - loss: 1.6129 - mean_absolute_error: 0.9463 - val_loss: 12.4551 - val_mean_absolute_error: 2.4448
Epoch 163/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.5040 - mean_absolute_error: 0.8908 - val_loss: 9.2868 - val_mean_absolute_error: 2.3023
Epoch 164/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.3789 - mean_absolute_error: 0.8696 - val_loss: 10.9330 - val_mean_absolute_error: 2.3142
Epoch 165/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.3122 - mean_absolute_error: 0.8140 - val_loss: 9.4694 - val_mean_absolute_error: 2.2638
Epoch 166/1000
7/7 [==============================] - 0s 33ms/step - loss: 1.3191 - mean_absolute_error: 0.8134 - val_loss: 11.0353 - val_mean_absolute_error: 2.3557
Epoch 167/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.3833 - mean_absolute_error: 0.8568 - val_loss: 8.5396 - val_mean_absolute_error: 2.2471
Epoch 168/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.3247 - mean_absolute_error: 0.8279 - val_loss: 12.7207 - val_mean_absolute_error: 2.5166
Epoch 169/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.4979 - mean_absolute_error: 0.8651 - val_loss: 9.2735 - val_mean_absolute_error: 2.3103
Epoch 170/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5321 - mean_absolute_error: 0.8986 - val_loss: 12.3985 - val_mean_absolute_error: 2.5691
Epoch 171/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.3644 - mean_absolute_error: 0.8693 - val_loss: 9.4814 - val_mean_absolute_error: 2.2611
Epoch 172/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.2811 - mean_absolute_error: 0.8008 - val_loss: 11.2137 - val_mean_absolute_error: 2.3523
Epoch 173/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2419 - mean_absolute_error: 0.7653 - val_loss: 9.7253 - val_mean_absolute_error: 2.2936
Epoch 174/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.3083 - mean_absolute_error: 0.8168 - val_loss: 10.6049 - val_mean_absolute_error: 2.3275
Epoch 175/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.3498 - mean_absolute_error: 0.8452 - val_loss: 9.6151 - val_mean_absolute_error: 2.2892
Epoch 176/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.3026 - mean_absolute_error: 0.8355 - val_loss: 11.4195 - val_mean_absolute_error: 2.3307
Epoch 177/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.4725 - mean_absolute_error: 0.8757 - val_loss: 9.2746 - val_mean_absolute_error: 2.3180
Epoch 178/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.4252 - mean_absolute_error: 0.9028 - val_loss: 13.4209 - val_mean_absolute_error: 2.5807
Epoch 179/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.3213 - mean_absolute_error: 0.8699 - val_loss: 9.4083 - val_mean_absolute_error: 2.3670
Epoch 180/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2920 - mean_absolute_error: 0.8422 - val_loss: 12.3839 - val_mean_absolute_error: 2.4383
Epoch 181/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.3021 - mean_absolute_error: 0.8464 - val_loss: 9.3092 - val_mean_absolute_error: 2.3388
Epoch 182/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2418 - mean_absolute_error: 0.8058 - val_loss: 11.3785 - val_mean_absolute_error: 2.3789
Epoch 183/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.3433 - mean_absolute_error: 0.8376 - val_loss: 10.1410 - val_mean_absolute_error: 2.3802
Epoch 184/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0902 - mean_absolute_error: 0.7399 - val_loss: 10.8392 - val_mean_absolute_error: 2.3478
Epoch 185/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.1362 - mean_absolute_error: 0.7299 - val_loss: 10.1163 - val_mean_absolute_error: 2.3214
Epoch 186/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.1429 - mean_absolute_error: 0.7440 - val_loss: 11.1999 - val_mean_absolute_error: 2.3442
Epoch 187/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0219 - mean_absolute_error: 0.7125 - val_loss: 11.1222 - val_mean_absolute_error: 2.3510
Epoch 188/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0204 - mean_absolute_error: 0.7054 - val_loss: 10.6766 - val_mean_absolute_error: 2.3815
Epoch 189/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0826 - mean_absolute_error: 0.7423 - val_loss: 11.4094 - val_mean_absolute_error: 2.3501
Epoch 190/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.9941 - mean_absolute_error: 0.6938 - val_loss: 9.8968 - val_mean_absolute_error: 2.3329
Epoch 191/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0106 - mean_absolute_error: 0.6997 - val_loss: 12.0554 - val_mean_absolute_error: 2.4215
Epoch 192/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9715 - mean_absolute_error: 0.6789 - val_loss: 10.2187 - val_mean_absolute_error: 2.3283
Epoch 193/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.9323 - mean_absolute_error: 0.6699 - val_loss: 10.6990 - val_mean_absolute_error: 2.3459
Epoch 194/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.9137 - mean_absolute_error: 0.6724 - val_loss: 10.9569 - val_mean_absolute_error: 2.3692
Epoch 195/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.9105 - mean_absolute_error: 0.6488 - val_loss: 10.9843 - val_mean_absolute_error: 2.3213
Epoch 196/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9223 - mean_absolute_error: 0.6754 - val_loss: 10.4069 - val_mean_absolute_error: 2.3061
Epoch 197/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.9931 - mean_absolute_error: 0.6987 - val_loss: 12.0836 - val_mean_absolute_error: 2.4336
Epoch 198/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0011 - mean_absolute_error: 0.7036 - val_loss: 9.8302 - val_mean_absolute_error: 2.3160
Epoch 199/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.9293 - mean_absolute_error: 0.6739 - val_loss: 12.9734 - val_mean_absolute_error: 2.4859
Epoch 200/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9500 - mean_absolute_error: 0.6830 - val_loss: 10.0728 - val_mean_absolute_error: 2.3548
Epoch 201/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8323 - mean_absolute_error: 0.6303 - val_loss: 11.6384 - val_mean_absolute_error: 2.3820
Epoch 202/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8124 - mean_absolute_error: 0.6098 - val_loss: 9.8363 - val_mean_absolute_error: 2.3292
Epoch 203/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8409 - mean_absolute_error: 0.6353 - val_loss: 11.9078 - val_mean_absolute_error: 2.4207
Epoch 204/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.8685 - mean_absolute_error: 0.6559 - val_loss: 11.0062 - val_mean_absolute_error: 2.3330
Epoch 205/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0066 - mean_absolute_error: 0.6724 - val_loss: 10.1528 - val_mean_absolute_error: 2.3004
Epoch 206/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.9779 - mean_absolute_error: 0.6938 - val_loss: 11.5405 - val_mean_absolute_error: 2.3483
Epoch 207/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0316 - mean_absolute_error: 0.7179 - val_loss: 10.5162 - val_mean_absolute_error: 2.3436
Epoch 208/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8511 - mean_absolute_error: 0.6315 - val_loss: 11.3080 - val_mean_absolute_error: 2.3700
Epoch 209/1000
7/7 [==============================] - 0s 24ms/step - loss: 1.0218 - mean_absolute_error: 0.6927 - val_loss: 11.2761 - val_mean_absolute_error: 2.3818
Epoch 210/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.9744 - mean_absolute_error: 0.6916 - val_loss: 10.8121 - val_mean_absolute_error: 2.4038
Epoch 211/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9938 - mean_absolute_error: 0.7117 - val_loss: 11.8017 - val_mean_absolute_error: 2.3834
Epoch 212/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9572 - mean_absolute_error: 0.7221 - val_loss: 10.7268 - val_mean_absolute_error: 2.3390
Epoch 213/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7668 - mean_absolute_error: 0.6138 - val_loss: 10.5396 - val_mean_absolute_error: 2.3335
Epoch 214/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8374 - mean_absolute_error: 0.6133 - val_loss: 11.6146 - val_mean_absolute_error: 2.3534
Epoch 215/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7648 - mean_absolute_error: 0.6058 - val_loss: 10.4798 - val_mean_absolute_error: 2.3424
Epoch 216/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7795 - mean_absolute_error: 0.6316 - val_loss: 11.7002 - val_mean_absolute_error: 2.4017
Epoch 217/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7397 - mean_absolute_error: 0.6131 - val_loss: 10.5399 - val_mean_absolute_error: 2.3490
Epoch 218/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.7368 - mean_absolute_error: 0.5830 - val_loss: 11.0356 - val_mean_absolute_error: 2.3571
Epoch 219/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.7606 - mean_absolute_error: 0.5989 - val_loss: 11.2188 - val_mean_absolute_error: 2.3931
Epoch 220/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7824 - mean_absolute_error: 0.6107 - val_loss: 10.8619 - val_mean_absolute_error: 2.3645
Epoch 221/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6697 - mean_absolute_error: 0.5534 - val_loss: 11.0655 - val_mean_absolute_error: 2.3646
Epoch 222/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7328 - mean_absolute_error: 0.5826 - val_loss: 12.3487 - val_mean_absolute_error: 2.4241
Epoch 223/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7441 - mean_absolute_error: 0.6072 - val_loss: 10.2585 - val_mean_absolute_error: 2.3857
Epoch 224/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8942 - mean_absolute_error: 0.6762 - val_loss: 13.2562 - val_mean_absolute_error: 2.4587
Epoch 225/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8483 - mean_absolute_error: 0.6623 - val_loss: 9.4447 - val_mean_absolute_error: 2.3353
Epoch 226/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7876 - mean_absolute_error: 0.6430 - val_loss: 13.1249 - val_mean_absolute_error: 2.4869
Epoch 227/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.9920 - mean_absolute_error: 0.7288 - val_loss: 10.8149 - val_mean_absolute_error: 2.3563
Epoch 228/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9776 - mean_absolute_error: 0.7029 - val_loss: 10.5787 - val_mean_absolute_error: 2.3044
Epoch 229/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9174 - mean_absolute_error: 0.6819 - val_loss: 11.1250 - val_mean_absolute_error: 2.3278
Epoch 230/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8385 - mean_absolute_error: 0.6376 - val_loss: 11.6145 - val_mean_absolute_error: 2.4082
Epoch 231/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8387 - mean_absolute_error: 0.6494 - val_loss: 11.4320 - val_mean_absolute_error: 2.3625
Epoch 232/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.2950 - mean_absolute_error: 0.7364 - val_loss: 10.5543 - val_mean_absolute_error: 2.3105
Epoch 233/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0108 - mean_absolute_error: 0.6561 - val_loss: 11.6974 - val_mean_absolute_error: 2.3798
Epoch 234/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9589 - mean_absolute_error: 0.6751 - val_loss: 10.2667 - val_mean_absolute_error: 2.3109
Epoch 235/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9978 - mean_absolute_error: 0.6865 - val_loss: 11.7137 - val_mean_absolute_error: 2.4145
Epoch 236/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.8874 - mean_absolute_error: 0.6617 - val_loss: 11.8787 - val_mean_absolute_error: 2.4164
Epoch 237/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8734 - mean_absolute_error: 0.6422 - val_loss: 11.5909 - val_mean_absolute_error: 2.3819
Epoch 238/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7995 - mean_absolute_error: 0.6213 - val_loss: 11.2184 - val_mean_absolute_error: 2.4047
Epoch 239/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9224 - mean_absolute_error: 0.6966 - val_loss: 11.5527 - val_mean_absolute_error: 2.3749
Epoch 240/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9326 - mean_absolute_error: 0.6982 - val_loss: 11.7216 - val_mean_absolute_error: 2.4346
Epoch 241/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8285 - mean_absolute_error: 0.6545 - val_loss: 11.4235 - val_mean_absolute_error: 2.4260
Epoch 242/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8877 - mean_absolute_error: 0.6861 - val_loss: 10.2112 - val_mean_absolute_error: 2.3503
Epoch 243/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7352 - mean_absolute_error: 0.6344 - val_loss: 13.3535 - val_mean_absolute_error: 2.5285
Epoch 244/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8763 - mean_absolute_error: 0.6793 - val_loss: 10.5138 - val_mean_absolute_error: 2.3902
Epoch 245/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7453 - mean_absolute_error: 0.6066 - val_loss: 11.6313 - val_mean_absolute_error: 2.4657
Epoch 246/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7740 - mean_absolute_error: 0.6507 - val_loss: 12.2183 - val_mean_absolute_error: 2.3939
Epoch 247/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7669 - mean_absolute_error: 0.6366 - val_loss: 10.3696 - val_mean_absolute_error: 2.3620
Epoch 248/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8221 - mean_absolute_error: 0.6537 - val_loss: 11.7141 - val_mean_absolute_error: 2.3773
Epoch 249/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6819 - mean_absolute_error: 0.5667 - val_loss: 11.3776 - val_mean_absolute_error: 2.3887
Epoch 250/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6643 - mean_absolute_error: 0.5662 - val_loss: 10.7070 - val_mean_absolute_error: 2.3462
Epoch 251/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6068 - mean_absolute_error: 0.5246 - val_loss: 11.6584 - val_mean_absolute_error: 2.4105
Epoch 252/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5644 - mean_absolute_error: 0.5005 - val_loss: 10.4692 - val_mean_absolute_error: 2.3279
Epoch 253/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5516 - mean_absolute_error: 0.4890 - val_loss: 11.7056 - val_mean_absolute_error: 2.3726
Epoch 254/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5933 - mean_absolute_error: 0.5034 - val_loss: 11.1393 - val_mean_absolute_error: 2.3806
Epoch 255/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5704 - mean_absolute_error: 0.5158 - val_loss: 11.3937 - val_mean_absolute_error: 2.3732
Epoch 256/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5451 - mean_absolute_error: 0.4960 - val_loss: 11.5957 - val_mean_absolute_error: 2.3803
Epoch 257/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5729 - mean_absolute_error: 0.5138 - val_loss: 11.0876 - val_mean_absolute_error: 2.3929
Epoch 258/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5886 - mean_absolute_error: 0.4906 - val_loss: 11.0813 - val_mean_absolute_error: 2.3754
Epoch 259/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5567 - mean_absolute_error: 0.4914 - val_loss: 11.4910 - val_mean_absolute_error: 2.3417
Epoch 260/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5455 - mean_absolute_error: 0.4947 - val_loss: 11.0118 - val_mean_absolute_error: 2.3887
Epoch 261/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5677 - mean_absolute_error: 0.4988 - val_loss: 11.1491 - val_mean_absolute_error: 2.3690
Epoch 262/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5089 - mean_absolute_error: 0.4851 - val_loss: 11.7201 - val_mean_absolute_error: 2.4086
Epoch 263/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.5551 - mean_absolute_error: 0.4951 - val_loss: 11.2738 - val_mean_absolute_error: 2.3933
Epoch 264/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.5591 - mean_absolute_error: 0.4885 - val_loss: 11.9995 - val_mean_absolute_error: 2.3939
Epoch 265/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.5210 - mean_absolute_error: 0.4859 - val_loss: 11.1052 - val_mean_absolute_error: 2.3610
Epoch 266/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.5464 - mean_absolute_error: 0.4674 - val_loss: 11.7420 - val_mean_absolute_error: 2.3572
Epoch 267/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.5365 - mean_absolute_error: 0.4891 - val_loss: 11.4066 - val_mean_absolute_error: 2.3907
Epoch 268/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.5525 - mean_absolute_error: 0.4881 - val_loss: 11.1991 - val_mean_absolute_error: 2.4205
Epoch 269/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.5601 - mean_absolute_error: 0.4878 - val_loss: 11.5078 - val_mean_absolute_error: 2.4029
Epoch 270/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.5117 - mean_absolute_error: 0.4644 - val_loss: 10.9876 - val_mean_absolute_error: 2.3552
Epoch 271/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5297 - mean_absolute_error: 0.4482 - val_loss: 11.5248 - val_mean_absolute_error: 2.4332
Epoch 272/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5703 - mean_absolute_error: 0.4953 - val_loss: 11.5160 - val_mean_absolute_error: 2.3818
Epoch 273/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5175 - mean_absolute_error: 0.4775 - val_loss: 11.4383 - val_mean_absolute_error: 2.4076
Epoch 274/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.6159 - mean_absolute_error: 0.5189 - val_loss: 11.4738 - val_mean_absolute_error: 2.3877
Epoch 275/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5882 - mean_absolute_error: 0.5401 - val_loss: 11.2920 - val_mean_absolute_error: 2.4213
Epoch 276/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6668 - mean_absolute_error: 0.5687 - val_loss: 11.8438 - val_mean_absolute_error: 2.3851
Epoch 277/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6864 - mean_absolute_error: 0.5692 - val_loss: 11.3314 - val_mean_absolute_error: 2.3892
Epoch 278/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6809 - mean_absolute_error: 0.5407 - val_loss: 12.5064 - val_mean_absolute_error: 2.4230
Epoch 279/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8419 - mean_absolute_error: 0.6385 - val_loss: 10.5786 - val_mean_absolute_error: 2.3774
Epoch 280/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8016 - mean_absolute_error: 0.6318 - val_loss: 12.0430 - val_mean_absolute_error: 2.4609
Epoch 281/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7531 - mean_absolute_error: 0.6055 - val_loss: 11.3457 - val_mean_absolute_error: 2.3972
Epoch 282/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.5539 - mean_absolute_error: 0.4995 - val_loss: 11.2367 - val_mean_absolute_error: 2.3344
Epoch 283/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5156 - mean_absolute_error: 0.4815 - val_loss: 11.3140 - val_mean_absolute_error: 2.3879
Epoch 284/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5235 - mean_absolute_error: 0.4722 - val_loss: 11.0977 - val_mean_absolute_error: 2.3688
Epoch 285/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5788 - mean_absolute_error: 0.5299 - val_loss: 11.8272 - val_mean_absolute_error: 2.4873
Epoch 286/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5484 - mean_absolute_error: 0.5040 - val_loss: 12.0022 - val_mean_absolute_error: 2.3902
Epoch 287/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7212 - mean_absolute_error: 0.6028 - val_loss: 10.4255 - val_mean_absolute_error: 2.3626
Epoch 288/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0294 - mean_absolute_error: 0.7520 - val_loss: 14.2674 - val_mean_absolute_error: 2.5792
Epoch 289/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0809 - mean_absolute_error: 0.7681 - val_loss: 10.9145 - val_mean_absolute_error: 2.3512
Epoch 290/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8108 - mean_absolute_error: 0.6155 - val_loss: 10.9787 - val_mean_absolute_error: 2.3796
Epoch 291/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6081 - mean_absolute_error: 0.5289 - val_loss: 12.0920 - val_mean_absolute_error: 2.4600
Epoch 292/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7104 - mean_absolute_error: 0.5584 - val_loss: 11.4036 - val_mean_absolute_error: 2.4487
Epoch 293/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5237 - mean_absolute_error: 0.4879 - val_loss: 11.9810 - val_mean_absolute_error: 2.4054
Epoch 294/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5486 - mean_absolute_error: 0.4952 - val_loss: 11.2963 - val_mean_absolute_error: 2.4158
Epoch 295/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6369 - mean_absolute_error: 0.5365 - val_loss: 10.7507 - val_mean_absolute_error: 2.3258
Epoch 296/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5360 - mean_absolute_error: 0.5006 - val_loss: 10.7204 - val_mean_absolute_error: 2.3196
Epoch 297/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4910 - mean_absolute_error: 0.4757 - val_loss: 12.1047 - val_mean_absolute_error: 2.4641
Epoch 298/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5380 - mean_absolute_error: 0.5020 - val_loss: 11.0781 - val_mean_absolute_error: 2.4766
Epoch 299/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5367 - mean_absolute_error: 0.4755 - val_loss: 11.5423 - val_mean_absolute_error: 2.3980
Epoch 300/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5091 - mean_absolute_error: 0.4583 - val_loss: 11.7307 - val_mean_absolute_error: 2.3859
Epoch 301/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4826 - mean_absolute_error: 0.4632 - val_loss: 11.3184 - val_mean_absolute_error: 2.4282
Epoch 302/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4443 - mean_absolute_error: 0.4123 - val_loss: 11.7519 - val_mean_absolute_error: 2.4301
Epoch 303/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4531 - mean_absolute_error: 0.4001 - val_loss: 11.5104 - val_mean_absolute_error: 2.4074
Epoch 304/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4182 - mean_absolute_error: 0.3851 - val_loss: 11.4232 - val_mean_absolute_error: 2.4350
Epoch 305/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3715 - mean_absolute_error: 0.3616 - val_loss: 11.4703 - val_mean_absolute_error: 2.4315
Epoch 306/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4242 - mean_absolute_error: 0.3754 - val_loss: 11.4124 - val_mean_absolute_error: 2.4376
Epoch 307/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3753 - mean_absolute_error: 0.3684 - val_loss: 11.5155 - val_mean_absolute_error: 2.4180
Epoch 308/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.3532 - mean_absolute_error: 0.3327 - val_loss: 11.2741 - val_mean_absolute_error: 2.3979
Epoch 309/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4292 - mean_absolute_error: 0.3930 - val_loss: 11.4567 - val_mean_absolute_error: 2.4137
Epoch 310/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4714 - mean_absolute_error: 0.4272 - val_loss: 10.9603 - val_mean_absolute_error: 2.3703
Epoch 311/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4604 - mean_absolute_error: 0.4350 - val_loss: 12.0402 - val_mean_absolute_error: 2.4925
Epoch 312/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4260 - mean_absolute_error: 0.4121 - val_loss: 12.0787 - val_mean_absolute_error: 2.4256
Epoch 313/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4004 - mean_absolute_error: 0.4063 - val_loss: 10.6818 - val_mean_absolute_error: 2.4335
Epoch 314/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4157 - mean_absolute_error: 0.4041 - val_loss: 11.5595 - val_mean_absolute_error: 2.4414
Epoch 315/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4830 - mean_absolute_error: 0.4383 - val_loss: 12.0514 - val_mean_absolute_error: 2.4207
Epoch 316/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4554 - mean_absolute_error: 0.4486 - val_loss: 10.7241 - val_mean_absolute_error: 2.3999
Epoch 317/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5685 - mean_absolute_error: 0.4704 - val_loss: 11.0345 - val_mean_absolute_error: 2.3548
Epoch 318/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4430 - mean_absolute_error: 0.4365 - val_loss: 11.7121 - val_mean_absolute_error: 2.4449
Epoch 319/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4963 - mean_absolute_error: 0.4565 - val_loss: 11.6632 - val_mean_absolute_error: 2.5158
Epoch 320/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4974 - mean_absolute_error: 0.4604 - val_loss: 11.7648 - val_mean_absolute_error: 2.5413
Epoch 321/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.5182 - mean_absolute_error: 0.4607 - val_loss: 10.9871 - val_mean_absolute_error: 2.3365
Epoch 322/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4913 - mean_absolute_error: 0.4836 - val_loss: 10.3400 - val_mean_absolute_error: 2.4562
Epoch 323/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4643 - mean_absolute_error: 0.4552 - val_loss: 12.3932 - val_mean_absolute_error: 2.5088
Epoch 324/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4633 - mean_absolute_error: 0.4484 - val_loss: 11.3897 - val_mean_absolute_error: 2.4169
Epoch 325/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3657 - mean_absolute_error: 0.3574 - val_loss: 11.4551 - val_mean_absolute_error: 2.4530
Epoch 326/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3540 - mean_absolute_error: 0.3644 - val_loss: 11.6783 - val_mean_absolute_error: 2.4756
Epoch 327/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4196 - mean_absolute_error: 0.3946 - val_loss: 11.0940 - val_mean_absolute_error: 2.4543
Epoch 328/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3810 - mean_absolute_error: 0.3811 - val_loss: 11.7823 - val_mean_absolute_error: 2.4387
Epoch 329/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4215 - mean_absolute_error: 0.3914 - val_loss: 11.2040 - val_mean_absolute_error: 2.4042
Epoch 330/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4348 - mean_absolute_error: 0.4367 - val_loss: 11.6861 - val_mean_absolute_error: 2.4418
Epoch 331/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4674 - mean_absolute_error: 0.4532 - val_loss: 11.6167 - val_mean_absolute_error: 2.3937
Epoch 332/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4979 - mean_absolute_error: 0.4872 - val_loss: 10.8883 - val_mean_absolute_error: 2.4425
Epoch 333/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4936 - mean_absolute_error: 0.4602 - val_loss: 12.4558 - val_mean_absolute_error: 2.4434
Epoch 334/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6286 - mean_absolute_error: 0.5422 - val_loss: 11.5065 - val_mean_absolute_error: 2.4772
Epoch 335/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6856 - mean_absolute_error: 0.5559 - val_loss: 11.5429 - val_mean_absolute_error: 2.4003
Epoch 336/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5267 - mean_absolute_error: 0.5030 - val_loss: 11.0380 - val_mean_absolute_error: 2.4157
Epoch 337/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5082 - mean_absolute_error: 0.4797 - val_loss: 11.5741 - val_mean_absolute_error: 2.4663
Epoch 338/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4798 - mean_absolute_error: 0.4565 - val_loss: 12.3408 - val_mean_absolute_error: 2.5039
Epoch 339/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5345 - mean_absolute_error: 0.5004 - val_loss: 11.3730 - val_mean_absolute_error: 2.5174
Epoch 340/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4773 - mean_absolute_error: 0.4755 - val_loss: 11.9888 - val_mean_absolute_error: 2.4190
Epoch 341/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4961 - mean_absolute_error: 0.5008 - val_loss: 11.2682 - val_mean_absolute_error: 2.4227
Epoch 342/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4296 - mean_absolute_error: 0.4347 - val_loss: 10.4518 - val_mean_absolute_error: 2.3275
Epoch 343/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4061 - mean_absolute_error: 0.4258 - val_loss: 11.9637 - val_mean_absolute_error: 2.4328
Epoch 344/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4335 - mean_absolute_error: 0.4202 - val_loss: 11.5839 - val_mean_absolute_error: 2.4083
Epoch 345/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3631 - mean_absolute_error: 0.3714 - val_loss: 11.1468 - val_mean_absolute_error: 2.3655
Epoch 346/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3899 - mean_absolute_error: 0.4051 - val_loss: 10.9427 - val_mean_absolute_error: 2.4056
Epoch 347/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3553 - mean_absolute_error: 0.3824 - val_loss: 11.1364 - val_mean_absolute_error: 2.4169
Epoch 348/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3845 - mean_absolute_error: 0.3977 - val_loss: 11.3469 - val_mean_absolute_error: 2.3815
Epoch 349/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4933 - mean_absolute_error: 0.4522 - val_loss: 11.2059 - val_mean_absolute_error: 2.4351
Epoch 350/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5541 - mean_absolute_error: 0.4674 - val_loss: 12.2018 - val_mean_absolute_error: 2.4542
Epoch 351/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6168 - mean_absolute_error: 0.4913 - val_loss: 10.5841 - val_mean_absolute_error: 2.3860
Epoch 352/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.6176 - mean_absolute_error: 0.5298 - val_loss: 11.4075 - val_mean_absolute_error: 2.4567
Epoch 353/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6048 - mean_absolute_error: 0.5118 - val_loss: 11.4411 - val_mean_absolute_error: 2.4243
Epoch 354/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6805 - mean_absolute_error: 0.5179 - val_loss: 10.8632 - val_mean_absolute_error: 2.4376
Epoch 355/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4256 - mean_absolute_error: 0.4540 - val_loss: 11.3947 - val_mean_absolute_error: 2.3953
Epoch 356/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7310 - mean_absolute_error: 0.5472 - val_loss: 11.1666 - val_mean_absolute_error: 2.3774
Epoch 357/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7117 - mean_absolute_error: 0.5753 - val_loss: 10.5130 - val_mean_absolute_error: 2.3363
Epoch 358/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6541 - mean_absolute_error: 0.5556 - val_loss: 12.4806 - val_mean_absolute_error: 2.4348
Epoch 359/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6038 - mean_absolute_error: 0.5067 - val_loss: 11.7450 - val_mean_absolute_error: 2.4953
Epoch 360/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.6527 - mean_absolute_error: 0.5136 - val_loss: 11.5350 - val_mean_absolute_error: 2.3760
Epoch 361/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5572 - mean_absolute_error: 0.4783 - val_loss: 11.4498 - val_mean_absolute_error: 2.4289
Epoch 362/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5464 - mean_absolute_error: 0.5037 - val_loss: 10.9167 - val_mean_absolute_error: 2.3598
Epoch 363/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4957 - mean_absolute_error: 0.4587 - val_loss: 11.6033 - val_mean_absolute_error: 2.3440
Epoch 364/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4894 - mean_absolute_error: 0.5000 - val_loss: 11.3201 - val_mean_absolute_error: 2.4333
Epoch 365/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4465 - mean_absolute_error: 0.4505 - val_loss: 11.4252 - val_mean_absolute_error: 2.3089
Epoch 366/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4521 - mean_absolute_error: 0.4316 - val_loss: 11.7963 - val_mean_absolute_error: 2.4411
Epoch 367/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4208 - mean_absolute_error: 0.4248 - val_loss: 11.0447 - val_mean_absolute_error: 2.3815
Epoch 368/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3431 - mean_absolute_error: 0.3751 - val_loss: 11.1455 - val_mean_absolute_error: 2.4061
Epoch 369/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3474 - mean_absolute_error: 0.3727 - val_loss: 12.4181 - val_mean_absolute_error: 2.4868
Epoch 370/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4040 - mean_absolute_error: 0.3971 - val_loss: 10.3001 - val_mean_absolute_error: 2.3777
Epoch 371/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3355 - mean_absolute_error: 0.3799 - val_loss: 11.5526 - val_mean_absolute_error: 2.4166
Epoch 372/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.3537 - mean_absolute_error: 0.3728 - val_loss: 11.5257 - val_mean_absolute_error: 2.4552
Epoch 373/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3280 - mean_absolute_error: 0.3405 - val_loss: 11.7271 - val_mean_absolute_error: 2.4397
Epoch 374/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3180 - mean_absolute_error: 0.3516 - val_loss: 10.9579 - val_mean_absolute_error: 2.3958
Epoch 375/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2959 - mean_absolute_error: 0.3152 - val_loss: 10.6487 - val_mean_absolute_error: 2.3868
Epoch 376/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2915 - mean_absolute_error: 0.3109 - val_loss: 11.5236 - val_mean_absolute_error: 2.3994
Epoch 377/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2786 - mean_absolute_error: 0.2984 - val_loss: 11.8209 - val_mean_absolute_error: 2.4165
Epoch 378/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3385 - mean_absolute_error: 0.3512 - val_loss: 10.9464 - val_mean_absolute_error: 2.3976
Epoch 379/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3282 - mean_absolute_error: 0.3581 - val_loss: 11.4201 - val_mean_absolute_error: 2.3843
Epoch 380/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4043 - mean_absolute_error: 0.4195 - val_loss: 11.0619 - val_mean_absolute_error: 2.4347
Epoch 381/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5052 - mean_absolute_error: 0.4805 - val_loss: 11.3217 - val_mean_absolute_error: 2.3383
Epoch 382/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4951 - mean_absolute_error: 0.4503 - val_loss: 11.5898 - val_mean_absolute_error: 2.4464
Epoch 383/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4769 - mean_absolute_error: 0.4613 - val_loss: 11.6396 - val_mean_absolute_error: 2.4075
Epoch 384/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4674 - mean_absolute_error: 0.4636 - val_loss: 11.1625 - val_mean_absolute_error: 2.4573
Epoch 385/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5351 - mean_absolute_error: 0.4729 - val_loss: 10.9256 - val_mean_absolute_error: 2.3613
Epoch 386/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4533 - mean_absolute_error: 0.4327 - val_loss: 12.3233 - val_mean_absolute_error: 2.4766
Epoch 387/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4315 - mean_absolute_error: 0.4543 - val_loss: 10.5881 - val_mean_absolute_error: 2.3698
Epoch 388/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3731 - mean_absolute_error: 0.4055 - val_loss: 11.4410 - val_mean_absolute_error: 2.4394
Epoch 389/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3321 - mean_absolute_error: 0.3663 - val_loss: 11.5417 - val_mean_absolute_error: 2.4327
Epoch 390/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2975 - mean_absolute_error: 0.3409 - val_loss: 11.0750 - val_mean_absolute_error: 2.4346
Epoch 391/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2806 - mean_absolute_error: 0.3042 - val_loss: 11.7707 - val_mean_absolute_error: 2.4262
Epoch 392/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2744 - mean_absolute_error: 0.3039 - val_loss: 11.0971 - val_mean_absolute_error: 2.4108
Epoch 393/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2796 - mean_absolute_error: 0.2861 - val_loss: 10.5036 - val_mean_absolute_error: 2.3630
Epoch 394/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2704 - mean_absolute_error: 0.3165 - val_loss: 11.3393 - val_mean_absolute_error: 2.4163
Epoch 395/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2547 - mean_absolute_error: 0.2878 - val_loss: 11.2621 - val_mean_absolute_error: 2.3625
Epoch 396/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3254 - mean_absolute_error: 0.3612 - val_loss: 11.0107 - val_mean_absolute_error: 2.4294
Epoch 397/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3456 - mean_absolute_error: 0.3492 - val_loss: 11.4579 - val_mean_absolute_error: 2.4197
Epoch 398/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3094 - mean_absolute_error: 0.3473 - val_loss: 11.0905 - val_mean_absolute_error: 2.4055
Epoch 399/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2618 - mean_absolute_error: 0.3037 - val_loss: 10.4984 - val_mean_absolute_error: 2.4045
Epoch 400/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2673 - mean_absolute_error: 0.3003 - val_loss: 12.6898 - val_mean_absolute_error: 2.5073
Epoch 401/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2950 - mean_absolute_error: 0.3232 - val_loss: 11.2901 - val_mean_absolute_error: 2.4352
Epoch 402/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2723 - mean_absolute_error: 0.3062 - val_loss: 11.0828 - val_mean_absolute_error: 2.4259
Epoch 403/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2745 - mean_absolute_error: 0.3190 - val_loss: 10.8430 - val_mean_absolute_error: 2.4255
Epoch 404/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2542 - mean_absolute_error: 0.2943 - val_loss: 12.0954 - val_mean_absolute_error: 2.4392
Epoch 405/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2601 - mean_absolute_error: 0.3091 - val_loss: 11.0178 - val_mean_absolute_error: 2.3886
Epoch 406/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2743 - mean_absolute_error: 0.3199 - val_loss: 11.2290 - val_mean_absolute_error: 2.4358
Epoch 407/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3483 - mean_absolute_error: 0.3007 - val_loss: 11.4351 - val_mean_absolute_error: 2.4601
Epoch 408/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.3337 - mean_absolute_error: 0.3348 - val_loss: 11.9482 - val_mean_absolute_error: 2.4819
Epoch 409/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.3785 - mean_absolute_error: 0.4159 - val_loss: 10.8934 - val_mean_absolute_error: 2.3683
Epoch 410/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.2863 - mean_absolute_error: 0.3381 - val_loss: 10.9836 - val_mean_absolute_error: 2.4051
Epoch 411/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.2687 - mean_absolute_error: 0.3150 - val_loss: 11.1602 - val_mean_absolute_error: 2.4255
Epoch 412/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.2987 - mean_absolute_error: 0.3148 - val_loss: 11.2066 - val_mean_absolute_error: 2.4034
Epoch 413/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.3875 - mean_absolute_error: 0.3713 - val_loss: 11.1264 - val_mean_absolute_error: 2.4205
Epoch 414/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3965 - mean_absolute_error: 0.3606 - val_loss: 11.2928 - val_mean_absolute_error: 2.3812
Epoch 415/1000
7/7 [==============================] - 0s 46ms/step - loss: 0.3210 - mean_absolute_error: 0.3325 - val_loss: 11.4350 - val_mean_absolute_error: 2.4837
Epoch 416/1000
7/7 [==============================] - 0s 42ms/step - loss: 0.3056 - mean_absolute_error: 0.3349 - val_loss: 11.5586 - val_mean_absolute_error: 2.4484
Epoch 417/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3456 - mean_absolute_error: 0.3627 - val_loss: 10.5583 - val_mean_absolute_error: 2.4038
Epoch 418/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3002 - mean_absolute_error: 0.3501 - val_loss: 11.2324 - val_mean_absolute_error: 2.4054
Epoch 419/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2878 - mean_absolute_error: 0.3239 - val_loss: 11.6943 - val_mean_absolute_error: 2.4646
Epoch 420/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3550 - mean_absolute_error: 0.3873 - val_loss: 11.4449 - val_mean_absolute_error: 2.4108
Epoch 421/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3579 - mean_absolute_error: 0.3887 - val_loss: 10.9414 - val_mean_absolute_error: 2.4580
Epoch 422/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3243 - mean_absolute_error: 0.3653 - val_loss: 11.4999 - val_mean_absolute_error: 2.4128
Epoch 423/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3554 - mean_absolute_error: 0.4015 - val_loss: 11.6130 - val_mean_absolute_error: 2.4420
Epoch 424/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3526 - mean_absolute_error: 0.3979 - val_loss: 10.8700 - val_mean_absolute_error: 2.3943
Epoch 425/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3468 - mean_absolute_error: 0.3838 - val_loss: 11.9776 - val_mean_absolute_error: 2.4657
Epoch 426/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3047 - mean_absolute_error: 0.3616 - val_loss: 11.0298 - val_mean_absolute_error: 2.3953
Epoch 427/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2908 - mean_absolute_error: 0.3227 - val_loss: 11.5800 - val_mean_absolute_error: 2.4712
Epoch 428/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3131 - mean_absolute_error: 0.3511 - val_loss: 10.8881 - val_mean_absolute_error: 2.3807
Epoch 429/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3524 - mean_absolute_error: 0.3910 - val_loss: 10.6831 - val_mean_absolute_error: 2.4108
Epoch 430/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4244 - mean_absolute_error: 0.4170 - val_loss: 11.3497 - val_mean_absolute_error: 2.3713
Epoch 431/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3796 - mean_absolute_error: 0.4229 - val_loss: 12.4195 - val_mean_absolute_error: 2.4913
Epoch 432/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4793 - mean_absolute_error: 0.4745 - val_loss: 10.9589 - val_mean_absolute_error: 2.4765
Epoch 433/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4958 - mean_absolute_error: 0.4816 - val_loss: 12.0481 - val_mean_absolute_error: 2.4951
Epoch 434/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3934 - mean_absolute_error: 0.4438 - val_loss: 12.6398 - val_mean_absolute_error: 2.4507
Epoch 435/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5230 - mean_absolute_error: 0.4863 - val_loss: 10.6652 - val_mean_absolute_error: 2.4363
Epoch 436/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4541 - mean_absolute_error: 0.4781 - val_loss: 10.8244 - val_mean_absolute_error: 2.3871
Epoch 437/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4945 - mean_absolute_error: 0.4637 - val_loss: 10.7797 - val_mean_absolute_error: 2.3891
Epoch 438/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4491 - mean_absolute_error: 0.4760 - val_loss: 11.4457 - val_mean_absolute_error: 2.4500
Epoch 439/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4389 - mean_absolute_error: 0.4436 - val_loss: 11.6313 - val_mean_absolute_error: 2.5263
Epoch 440/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4304 - mean_absolute_error: 0.4102 - val_loss: 11.3471 - val_mean_absolute_error: 2.4422
Epoch 441/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3893 - mean_absolute_error: 0.4143 - val_loss: 11.0962 - val_mean_absolute_error: 2.3339
Epoch 442/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3528 - mean_absolute_error: 0.4096 - val_loss: 10.4346 - val_mean_absolute_error: 2.3480
Epoch 443/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2951 - mean_absolute_error: 0.3321 - val_loss: 10.8426 - val_mean_absolute_error: 2.3635
Epoch 444/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2515 - mean_absolute_error: 0.3143 - val_loss: 10.9943 - val_mean_absolute_error: 2.3716
Epoch 445/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3019 - mean_absolute_error: 0.3476 - val_loss: 10.7065 - val_mean_absolute_error: 2.3767
Epoch 446/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2480 - mean_absolute_error: 0.3102 - val_loss: 11.1834 - val_mean_absolute_error: 2.3833
Epoch 447/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2703 - mean_absolute_error: 0.3125 - val_loss: 11.0339 - val_mean_absolute_error: 2.4033
Epoch 448/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2485 - mean_absolute_error: 0.3047 - val_loss: 10.7502 - val_mean_absolute_error: 2.4055
Epoch 449/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2331 - mean_absolute_error: 0.2835 - val_loss: 11.7565 - val_mean_absolute_error: 2.4402
Epoch 450/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2302 - mean_absolute_error: 0.2915 - val_loss: 10.6879 - val_mean_absolute_error: 2.3667
Epoch 451/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.2575 - mean_absolute_error: 0.3008 - val_loss: 11.1571 - val_mean_absolute_error: 2.3860
Epoch 452/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3191 - mean_absolute_error: 0.3368 - val_loss: 10.8119 - val_mean_absolute_error: 2.3956
Epoch 453/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3369 - mean_absolute_error: 0.3868 - val_loss: 11.4559 - val_mean_absolute_error: 2.4103
Epoch 454/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2988 - mean_absolute_error: 0.3438 - val_loss: 10.9658 - val_mean_absolute_error: 2.4179
Epoch 455/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2445 - mean_absolute_error: 0.3019 - val_loss: 10.5141 - val_mean_absolute_error: 2.3495
Epoch 456/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2187 - mean_absolute_error: 0.2878 - val_loss: 10.8835 - val_mean_absolute_error: 2.3785
Epoch 457/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2088 - mean_absolute_error: 0.2501 - val_loss: 10.9730 - val_mean_absolute_error: 2.3922
Epoch 458/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2449 - mean_absolute_error: 0.2862 - val_loss: 11.1979 - val_mean_absolute_error: 2.4425
Epoch 459/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2486 - mean_absolute_error: 0.3217 - val_loss: 10.9623 - val_mean_absolute_error: 2.3785
Epoch 460/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2655 - mean_absolute_error: 0.3205 - val_loss: 10.8356 - val_mean_absolute_error: 2.4118
Epoch 461/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2673 - mean_absolute_error: 0.3108 - val_loss: 10.9911 - val_mean_absolute_error: 2.4149
Epoch 462/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2634 - mean_absolute_error: 0.3070 - val_loss: 11.8809 - val_mean_absolute_error: 2.4403
Epoch 463/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2233 - mean_absolute_error: 0.3253 - val_loss: 10.3207 - val_mean_absolute_error: 2.3892
Epoch 464/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3499 - mean_absolute_error: 0.3870 - val_loss: 11.3842 - val_mean_absolute_error: 2.4285
Epoch 465/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2714 - mean_absolute_error: 0.3115 - val_loss: 11.0138 - val_mean_absolute_error: 2.4292
Epoch 466/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2496 - mean_absolute_error: 0.3044 - val_loss: 10.7433 - val_mean_absolute_error: 2.3913
Epoch 467/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2505 - mean_absolute_error: 0.3080 - val_loss: 10.6921 - val_mean_absolute_error: 2.3868
Epoch 468/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2177 - mean_absolute_error: 0.2795 - val_loss: 11.3918 - val_mean_absolute_error: 2.4245
Epoch 469/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2186 - mean_absolute_error: 0.2903 - val_loss: 10.6068 - val_mean_absolute_error: 2.3629
Epoch 470/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2308 - mean_absolute_error: 0.3094 - val_loss: 10.4585 - val_mean_absolute_error: 2.4104
Epoch 471/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2410 - mean_absolute_error: 0.3197 - val_loss: 11.1824 - val_mean_absolute_error: 2.3972
Epoch 472/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2591 - mean_absolute_error: 0.3413 - val_loss: 10.8990 - val_mean_absolute_error: 2.4190
Epoch 473/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3700 - mean_absolute_error: 0.4248 - val_loss: 10.3245 - val_mean_absolute_error: 2.3382
Epoch 474/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4597 - mean_absolute_error: 0.5023 - val_loss: 11.3989 - val_mean_absolute_error: 2.4428
Epoch 475/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4995 - mean_absolute_error: 0.5349 - val_loss: 11.7424 - val_mean_absolute_error: 2.4074
Epoch 476/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.5943 - mean_absolute_error: 0.5040 - val_loss: 10.4811 - val_mean_absolute_error: 2.3259
Epoch 477/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.3776 - mean_absolute_error: 0.4322 - val_loss: 10.2311 - val_mean_absolute_error: 2.3991
Epoch 478/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.5794 - mean_absolute_error: 0.5245 - val_loss: 11.3172 - val_mean_absolute_error: 2.3519
Epoch 479/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5610 - mean_absolute_error: 0.5078 - val_loss: 11.3596 - val_mean_absolute_error: 2.4231
Epoch 480/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6218 - mean_absolute_error: 0.5574 - val_loss: 11.7683 - val_mean_absolute_error: 2.5015
Epoch 481/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5077 - mean_absolute_error: 0.5431 - val_loss: 10.2371 - val_mean_absolute_error: 2.3717
Epoch 482/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4642 - mean_absolute_error: 0.4809 - val_loss: 10.7639 - val_mean_absolute_error: 2.4091
Epoch 483/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4266 - mean_absolute_error: 0.4757 - val_loss: 11.2383 - val_mean_absolute_error: 2.4401
Epoch 484/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3289 - mean_absolute_error: 0.4115 - val_loss: 11.6744 - val_mean_absolute_error: 2.4729
Epoch 485/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.2509 - mean_absolute_error: 0.3357 - val_loss: 11.1153 - val_mean_absolute_error: 2.4385
Epoch 486/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2024 - mean_absolute_error: 0.2923 - val_loss: 11.2780 - val_mean_absolute_error: 2.4334
Epoch 487/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2661 - mean_absolute_error: 0.3363 - val_loss: 11.5768 - val_mean_absolute_error: 2.4938
Epoch 488/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2738 - mean_absolute_error: 0.3323 - val_loss: 10.4752 - val_mean_absolute_error: 2.3874
Epoch 489/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2605 - mean_absolute_error: 0.3567 - val_loss: 11.1890 - val_mean_absolute_error: 2.4792
Epoch 490/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2568 - mean_absolute_error: 0.3167 - val_loss: 11.6768 - val_mean_absolute_error: 2.4557
Epoch 491/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2807 - mean_absolute_error: 0.3554 - val_loss: 10.4664 - val_mean_absolute_error: 2.3817
Epoch 492/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.5132 - mean_absolute_error: 0.4691 - val_loss: 10.7737 - val_mean_absolute_error: 2.4251
Epoch 493/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1414 - mean_absolute_error: 0.6213 - val_loss: 10.0009 - val_mean_absolute_error: 2.2913
Epoch 494/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2965 - mean_absolute_error: 0.6682 - val_loss: 10.7657 - val_mean_absolute_error: 2.3128
Epoch 495/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7426 - mean_absolute_error: 0.5946 - val_loss: 10.5852 - val_mean_absolute_error: 2.4677
Epoch 496/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.2347 - mean_absolute_error: 0.6845 - val_loss: 13.0383 - val_mean_absolute_error: 2.6146
Epoch 497/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0677 - mean_absolute_error: 0.6965 - val_loss: 10.3251 - val_mean_absolute_error: 2.3729
Epoch 498/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.6174 - mean_absolute_error: 0.5545 - val_loss: 10.5347 - val_mean_absolute_error: 2.3208
Epoch 499/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5709 - mean_absolute_error: 0.4731 - val_loss: 11.0227 - val_mean_absolute_error: 2.4749
Epoch 500/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5928 - mean_absolute_error: 0.4941 - val_loss: 10.8545 - val_mean_absolute_error: 2.4753
Epoch 501/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6578 - mean_absolute_error: 0.4706 - val_loss: 10.6884 - val_mean_absolute_error: 2.4361
Epoch 502/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3514 - mean_absolute_error: 0.3761 - val_loss: 11.1258 - val_mean_absolute_error: 2.4390
Epoch 503/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2514 - mean_absolute_error: 0.3356 - val_loss: 11.1195 - val_mean_absolute_error: 2.4863
Epoch 504/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2671 - mean_absolute_error: 0.3320 - val_loss: 11.0305 - val_mean_absolute_error: 2.4513
Epoch 505/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2320 - mean_absolute_error: 0.3169 - val_loss: 10.5155 - val_mean_absolute_error: 2.4560
Epoch 506/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2125 - mean_absolute_error: 0.2766 - val_loss: 10.8594 - val_mean_absolute_error: 2.4171
Epoch 507/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1808 - mean_absolute_error: 0.2515 - val_loss: 11.3981 - val_mean_absolute_error: 2.4492
Epoch 508/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2020 - mean_absolute_error: 0.2683 - val_loss: 10.7500 - val_mean_absolute_error: 2.4361
Epoch 509/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1623 - mean_absolute_error: 0.2226 - val_loss: 10.8058 - val_mean_absolute_error: 2.4585
Epoch 510/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1987 - mean_absolute_error: 0.2485 - val_loss: 11.5932 - val_mean_absolute_error: 2.4611
Epoch 511/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1668 - mean_absolute_error: 0.2423 - val_loss: 10.6005 - val_mean_absolute_error: 2.4158
Epoch 512/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2096 - mean_absolute_error: 0.2663 - val_loss: 11.1027 - val_mean_absolute_error: 2.4869
Epoch 513/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1855 - mean_absolute_error: 0.2710 - val_loss: 11.7942 - val_mean_absolute_error: 2.4967
Epoch 514/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2016 - mean_absolute_error: 0.2651 - val_loss: 10.6561 - val_mean_absolute_error: 2.4307
Epoch 515/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2128 - mean_absolute_error: 0.2816 - val_loss: 10.8392 - val_mean_absolute_error: 2.4147
Epoch 516/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2578 - mean_absolute_error: 0.2864 - val_loss: 11.0293 - val_mean_absolute_error: 2.4219
Epoch 517/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2459 - mean_absolute_error: 0.3032 - val_loss: 10.5899 - val_mean_absolute_error: 2.3986
Epoch 518/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1938 - mean_absolute_error: 0.2880 - val_loss: 10.7083 - val_mean_absolute_error: 2.3718
Epoch 519/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1978 - mean_absolute_error: 0.2470 - val_loss: 10.6944 - val_mean_absolute_error: 2.4284
Epoch 520/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2449 - mean_absolute_error: 0.2992 - val_loss: 10.8029 - val_mean_absolute_error: 2.4218
Epoch 521/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3043 - mean_absolute_error: 0.2851 - val_loss: 10.5553 - val_mean_absolute_error: 2.3780
Epoch 522/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2401 - mean_absolute_error: 0.2500 - val_loss: 10.6515 - val_mean_absolute_error: 2.4264
Epoch 523/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2676 - mean_absolute_error: 0.2670 - val_loss: 11.0529 - val_mean_absolute_error: 2.4669
Epoch 524/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2145 - mean_absolute_error: 0.2372 - val_loss: 10.6483 - val_mean_absolute_error: 2.4173
Epoch 525/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.2018 - mean_absolute_error: 0.2286 - val_loss: 10.7894 - val_mean_absolute_error: 2.4448
Epoch 526/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1999 - mean_absolute_error: 0.2255 - val_loss: 11.0898 - val_mean_absolute_error: 2.4213
Epoch 527/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1873 - mean_absolute_error: 0.2198 - val_loss: 10.4409 - val_mean_absolute_error: 2.4020
Epoch 528/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1936 - mean_absolute_error: 0.2215 - val_loss: 10.6952 - val_mean_absolute_error: 2.4403
Epoch 529/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2020 - mean_absolute_error: 0.2447 - val_loss: 11.5261 - val_mean_absolute_error: 2.4871
Epoch 530/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1992 - mean_absolute_error: 0.2316 - val_loss: 10.9164 - val_mean_absolute_error: 2.4746
Epoch 531/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1985 - mean_absolute_error: 0.2282 - val_loss: 10.7390 - val_mean_absolute_error: 2.4189
Epoch 532/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1990 - mean_absolute_error: 0.2455 - val_loss: 10.7981 - val_mean_absolute_error: 2.4432
Epoch 533/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1717 - mean_absolute_error: 0.2132 - val_loss: 10.8410 - val_mean_absolute_error: 2.4046
Epoch 534/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.1701 - mean_absolute_error: 0.2069 - val_loss: 10.4137 - val_mean_absolute_error: 2.3980
Epoch 535/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1640 - mean_absolute_error: 0.1989 - val_loss: 10.6653 - val_mean_absolute_error: 2.4326
Epoch 536/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1583 - mean_absolute_error: 0.1986 - val_loss: 10.8325 - val_mean_absolute_error: 2.4327
Epoch 537/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1640 - mean_absolute_error: 0.1925 - val_loss: 10.9230 - val_mean_absolute_error: 2.4260
Epoch 538/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1725 - mean_absolute_error: 0.2041 - val_loss: 10.9389 - val_mean_absolute_error: 2.4424
Epoch 539/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1624 - mean_absolute_error: 0.1960 - val_loss: 10.7745 - val_mean_absolute_error: 2.4465
Epoch 540/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1656 - mean_absolute_error: 0.1971 - val_loss: 10.7641 - val_mean_absolute_error: 2.4457
Epoch 541/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1540 - mean_absolute_error: 0.1867 - val_loss: 11.0202 - val_mean_absolute_error: 2.4479
Epoch 542/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1453 - mean_absolute_error: 0.1683 - val_loss: 10.7896 - val_mean_absolute_error: 2.4557
Epoch 543/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1627 - mean_absolute_error: 0.1911 - val_loss: 10.7662 - val_mean_absolute_error: 2.4474
Epoch 544/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1759 - mean_absolute_error: 0.2284 - val_loss: 10.9228 - val_mean_absolute_error: 2.4310
Epoch 545/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1936 - mean_absolute_error: 0.2393 - val_loss: 10.9231 - val_mean_absolute_error: 2.4637
Epoch 546/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2406 - mean_absolute_error: 0.2836 - val_loss: 10.9241 - val_mean_absolute_error: 2.4297
Epoch 547/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2491 - mean_absolute_error: 0.2936 - val_loss: 11.0189 - val_mean_absolute_error: 2.4921
Epoch 548/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2727 - mean_absolute_error: 0.2936 - val_loss: 10.3740 - val_mean_absolute_error: 2.3842
Epoch 549/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.2111 - mean_absolute_error: 0.2725 - val_loss: 10.5584 - val_mean_absolute_error: 2.3814
Epoch 550/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.2125 - mean_absolute_error: 0.2756 - val_loss: 11.0229 - val_mean_absolute_error: 2.4394
Epoch 551/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1966 - mean_absolute_error: 0.2602 - val_loss: 10.5799 - val_mean_absolute_error: 2.4051
Epoch 552/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.2072 - mean_absolute_error: 0.2698 - val_loss: 11.1516 - val_mean_absolute_error: 2.4448
Epoch 553/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2305 - mean_absolute_error: 0.3032 - val_loss: 10.3441 - val_mean_absolute_error: 2.3893
Epoch 554/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.2194 - mean_absolute_error: 0.2936 - val_loss: 11.1145 - val_mean_absolute_error: 2.4066
Epoch 555/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1876 - mean_absolute_error: 0.2650 - val_loss: 10.8691 - val_mean_absolute_error: 2.3955
Epoch 556/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1924 - mean_absolute_error: 0.2629 - val_loss: 10.8592 - val_mean_absolute_error: 2.4251
Epoch 557/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1789 - mean_absolute_error: 0.2385 - val_loss: 10.1336 - val_mean_absolute_error: 2.3885
Epoch 558/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1750 - mean_absolute_error: 0.2238 - val_loss: 11.1209 - val_mean_absolute_error: 2.4217
Epoch 559/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1529 - mean_absolute_error: 0.2097 - val_loss: 10.5811 - val_mean_absolute_error: 2.4095
Epoch 560/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1531 - mean_absolute_error: 0.1962 - val_loss: 10.8072 - val_mean_absolute_error: 2.4472
Epoch 561/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1573 - mean_absolute_error: 0.1978 - val_loss: 10.9593 - val_mean_absolute_error: 2.4025
Epoch 562/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1957 - mean_absolute_error: 0.2393 - val_loss: 10.8359 - val_mean_absolute_error: 2.4360
Epoch 563/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2017 - mean_absolute_error: 0.2641 - val_loss: 10.6207 - val_mean_absolute_error: 2.4344
Epoch 564/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2295 - mean_absolute_error: 0.3032 - val_loss: 10.6688 - val_mean_absolute_error: 2.3998
Epoch 565/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1961 - mean_absolute_error: 0.2814 - val_loss: 11.6109 - val_mean_absolute_error: 2.4728
Epoch 566/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1963 - mean_absolute_error: 0.2809 - val_loss: 10.4254 - val_mean_absolute_error: 2.3932
Epoch 567/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1677 - mean_absolute_error: 0.2523 - val_loss: 10.3427 - val_mean_absolute_error: 2.4071
Epoch 568/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1915 - mean_absolute_error: 0.2952 - val_loss: 10.5814 - val_mean_absolute_error: 2.3631
Epoch 569/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1996 - mean_absolute_error: 0.2868 - val_loss: 11.2250 - val_mean_absolute_error: 2.4102
Epoch 570/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1778 - mean_absolute_error: 0.2580 - val_loss: 10.5377 - val_mean_absolute_error: 2.3737
Epoch 571/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1772 - mean_absolute_error: 0.2348 - val_loss: 10.7093 - val_mean_absolute_error: 2.3965
Epoch 572/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1737 - mean_absolute_error: 0.2352 - val_loss: 11.0808 - val_mean_absolute_error: 2.4205
Epoch 573/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1875 - mean_absolute_error: 0.2558 - val_loss: 10.6566 - val_mean_absolute_error: 2.4274
Epoch 574/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1663 - mean_absolute_error: 0.2357 - val_loss: 11.0931 - val_mean_absolute_error: 2.4194
Epoch 575/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1447 - mean_absolute_error: 0.2134 - val_loss: 10.7053 - val_mean_absolute_error: 2.3929
Epoch 576/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1531 - mean_absolute_error: 0.2130 - val_loss: 10.3977 - val_mean_absolute_error: 2.4253
Epoch 577/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1630 - mean_absolute_error: 0.2346 - val_loss: 11.2719 - val_mean_absolute_error: 2.4334
Epoch 578/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1819 - mean_absolute_error: 0.2603 - val_loss: 10.5289 - val_mean_absolute_error: 2.3532
Epoch 579/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1867 - mean_absolute_error: 0.2694 - val_loss: 10.1717 - val_mean_absolute_error: 2.4058
Epoch 580/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2370 - mean_absolute_error: 0.3178 - val_loss: 10.6675 - val_mean_absolute_error: 2.4338
Epoch 581/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1923 - mean_absolute_error: 0.2825 - val_loss: 11.1273 - val_mean_absolute_error: 2.3732
Epoch 582/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2191 - mean_absolute_error: 0.3179 - val_loss: 10.2221 - val_mean_absolute_error: 2.3042
Epoch 583/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2213 - mean_absolute_error: 0.3061 - val_loss: 10.4859 - val_mean_absolute_error: 2.4243
Epoch 584/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.1869 - mean_absolute_error: 0.2850 - val_loss: 11.6966 - val_mean_absolute_error: 2.4295
Epoch 585/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2168 - mean_absolute_error: 0.3091 - val_loss: 10.4318 - val_mean_absolute_error: 2.3474
Epoch 586/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1781 - mean_absolute_error: 0.2650 - val_loss: 10.5476 - val_mean_absolute_error: 2.4187
Epoch 587/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1597 - mean_absolute_error: 0.2584 - val_loss: 10.7476 - val_mean_absolute_error: 2.4137
Epoch 588/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.1465 - mean_absolute_error: 0.2341 - val_loss: 10.4324 - val_mean_absolute_error: 2.3849
Epoch 589/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1619 - mean_absolute_error: 0.2445 - val_loss: 10.3573 - val_mean_absolute_error: 2.3677
Epoch 590/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1667 - mean_absolute_error: 0.2596 - val_loss: 10.3388 - val_mean_absolute_error: 2.3814
Epoch 591/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2903 - mean_absolute_error: 0.3244 - val_loss: 10.9728 - val_mean_absolute_error: 2.4183
Epoch 592/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2065 - mean_absolute_error: 0.3152 - val_loss: 11.0100 - val_mean_absolute_error: 2.3455
Epoch 593/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2052 - mean_absolute_error: 0.3097 - val_loss: 10.5415 - val_mean_absolute_error: 2.3639
Epoch 594/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1628 - mean_absolute_error: 0.2530 - val_loss: 10.4131 - val_mean_absolute_error: 2.4191
Epoch 595/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2421 - mean_absolute_error: 0.2691 - val_loss: 11.6567 - val_mean_absolute_error: 2.4987
Epoch 596/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.2055 - mean_absolute_error: 0.2890 - val_loss: 10.4084 - val_mean_absolute_error: 2.4176
Epoch 597/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1310 - mean_absolute_error: 0.2635 - val_loss: 10.0647 - val_mean_absolute_error: 2.3447
Epoch 598/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1781 - mean_absolute_error: 0.2363 - val_loss: 10.8444 - val_mean_absolute_error: 2.4112
Epoch 599/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1549 - mean_absolute_error: 0.2526 - val_loss: 10.4082 - val_mean_absolute_error: 2.3908
Epoch 600/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2211 - mean_absolute_error: 0.2852 - val_loss: 10.9334 - val_mean_absolute_error: 2.4205
Epoch 601/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2272 - mean_absolute_error: 0.3043 - val_loss: 11.1079 - val_mean_absolute_error: 2.5064
Epoch 602/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1807 - mean_absolute_error: 0.2923 - val_loss: 10.6917 - val_mean_absolute_error: 2.3961
Epoch 603/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2176 - mean_absolute_error: 0.3070 - val_loss: 9.9970 - val_mean_absolute_error: 2.3088
Epoch 604/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2949 - mean_absolute_error: 0.3834 - val_loss: 10.9545 - val_mean_absolute_error: 2.3861
Epoch 605/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.5294 - mean_absolute_error: 0.4159 - val_loss: 10.4197 - val_mean_absolute_error: 2.4002
Epoch 606/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3624 - mean_absolute_error: 0.3747 - val_loss: 10.3236 - val_mean_absolute_error: 2.3832
Epoch 607/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3789 - mean_absolute_error: 0.4219 - val_loss: 10.5872 - val_mean_absolute_error: 2.3677
Epoch 608/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2710 - mean_absolute_error: 0.3415 - val_loss: 10.4506 - val_mean_absolute_error: 2.3824
Epoch 609/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2370 - mean_absolute_error: 0.3277 - val_loss: 10.8797 - val_mean_absolute_error: 2.4055
Epoch 610/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3320 - mean_absolute_error: 0.3776 - val_loss: 10.2735 - val_mean_absolute_error: 2.3267
Epoch 611/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3089 - mean_absolute_error: 0.3234 - val_loss: 10.6515 - val_mean_absolute_error: 2.4454
Epoch 612/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2457 - mean_absolute_error: 0.3061 - val_loss: 11.1509 - val_mean_absolute_error: 2.4476
Epoch 613/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2257 - mean_absolute_error: 0.3120 - val_loss: 11.0395 - val_mean_absolute_error: 2.3650
Epoch 614/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2132 - mean_absolute_error: 0.2952 - val_loss: 9.8566 - val_mean_absolute_error: 2.3550
Epoch 615/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1763 - mean_absolute_error: 0.2639 - val_loss: 11.1696 - val_mean_absolute_error: 2.4027
Epoch 616/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1864 - mean_absolute_error: 0.2506 - val_loss: 10.2579 - val_mean_absolute_error: 2.3726
Epoch 617/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1458 - mean_absolute_error: 0.2316 - val_loss: 10.6550 - val_mean_absolute_error: 2.3809
Epoch 618/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1794 - mean_absolute_error: 0.2606 - val_loss: 10.4313 - val_mean_absolute_error: 2.3773
Epoch 619/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1302 - mean_absolute_error: 0.2093 - val_loss: 10.7186 - val_mean_absolute_error: 2.3554
Epoch 620/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1709 - mean_absolute_error: 0.2624 - val_loss: 10.5483 - val_mean_absolute_error: 2.4136
Epoch 621/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2480 - mean_absolute_error: 0.2700 - val_loss: 10.9082 - val_mean_absolute_error: 2.4279
Epoch 622/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2125 - mean_absolute_error: 0.2656 - val_loss: 10.8669 - val_mean_absolute_error: 2.4106
Epoch 623/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2400 - mean_absolute_error: 0.3201 - val_loss: 10.2469 - val_mean_absolute_error: 2.3713
Epoch 624/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2208 - mean_absolute_error: 0.2993 - val_loss: 10.1343 - val_mean_absolute_error: 2.3921
Epoch 625/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1895 - mean_absolute_error: 0.2872 - val_loss: 10.8433 - val_mean_absolute_error: 2.3603
Epoch 626/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1594 - mean_absolute_error: 0.2610 - val_loss: 10.3551 - val_mean_absolute_error: 2.3417
Epoch 627/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1650 - mean_absolute_error: 0.2668 - val_loss: 10.7673 - val_mean_absolute_error: 2.4409
Epoch 628/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1567 - mean_absolute_error: 0.2648 - val_loss: 10.4859 - val_mean_absolute_error: 2.3958
Epoch 629/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1734 - mean_absolute_error: 0.2621 - val_loss: 10.2074 - val_mean_absolute_error: 2.3479
Epoch 630/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1597 - mean_absolute_error: 0.2549 - val_loss: 10.8053 - val_mean_absolute_error: 2.4274
Epoch 631/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1642 - mean_absolute_error: 0.2387 - val_loss: 10.1906 - val_mean_absolute_error: 2.3857
Epoch 632/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1940 - mean_absolute_error: 0.2424 - val_loss: 10.8726 - val_mean_absolute_error: 2.4334
Epoch 633/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1265 - mean_absolute_error: 0.2126 - val_loss: 10.5198 - val_mean_absolute_error: 2.3804
Epoch 634/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.1541 - mean_absolute_error: 0.2284 - val_loss: 10.2164 - val_mean_absolute_error: 2.3846
Epoch 635/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1558 - mean_absolute_error: 0.2229 - val_loss: 10.6983 - val_mean_absolute_error: 2.3936
Epoch 636/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.1231 - mean_absolute_error: 0.2026 - val_loss: 10.8690 - val_mean_absolute_error: 2.3920
Epoch 637/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1275 - mean_absolute_error: 0.2120 - val_loss: 10.3428 - val_mean_absolute_error: 2.3743
Epoch 638/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1141 - mean_absolute_error: 0.1981 - val_loss: 10.5270 - val_mean_absolute_error: 2.4340
Epoch 639/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1395 - mean_absolute_error: 0.2368 - val_loss: 10.7693 - val_mean_absolute_error: 2.4036
Epoch 640/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1651 - mean_absolute_error: 0.2408 - val_loss: 11.0505 - val_mean_absolute_error: 2.4186
Epoch 641/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1771 - mean_absolute_error: 0.2684 - val_loss: 10.7984 - val_mean_absolute_error: 2.4216
Epoch 642/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4065 - mean_absolute_error: 0.3267 - val_loss: 10.0861 - val_mean_absolute_error: 2.3806
Epoch 643/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.6630 - mean_absolute_error: 0.5140 - val_loss: 11.2814 - val_mean_absolute_error: 2.4632
Epoch 644/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8701 - mean_absolute_error: 0.6632 - val_loss: 9.7917 - val_mean_absolute_error: 2.2589
Epoch 645/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0156 - mean_absolute_error: 0.6966 - val_loss: 10.1369 - val_mean_absolute_error: 2.3359
Epoch 646/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8906 - mean_absolute_error: 0.6485 - val_loss: 11.6958 - val_mean_absolute_error: 2.5631
Epoch 647/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.6180 - mean_absolute_error: 0.5538 - val_loss: 10.6844 - val_mean_absolute_error: 2.4120
Epoch 648/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5017 - mean_absolute_error: 0.4954 - val_loss: 10.3190 - val_mean_absolute_error: 2.3770
Epoch 649/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4223 - mean_absolute_error: 0.4578 - val_loss: 9.5874 - val_mean_absolute_error: 2.3471
Epoch 650/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3400 - mean_absolute_error: 0.4074 - val_loss: 9.2518 - val_mean_absolute_error: 2.3292
Epoch 651/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4383 - mean_absolute_error: 0.4640 - val_loss: 9.5912 - val_mean_absolute_error: 2.3872
Epoch 652/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4543 - mean_absolute_error: 0.4849 - val_loss: 10.7935 - val_mean_absolute_error: 2.4138
Epoch 653/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3728 - mean_absolute_error: 0.4489 - val_loss: 10.1092 - val_mean_absolute_error: 2.2988
Epoch 654/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3604 - mean_absolute_error: 0.4186 - val_loss: 9.7246 - val_mean_absolute_error: 2.3044
Epoch 655/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3067 - mean_absolute_error: 0.3879 - val_loss: 10.3488 - val_mean_absolute_error: 2.4429
Epoch 656/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2632 - mean_absolute_error: 0.3525 - val_loss: 11.1931 - val_mean_absolute_error: 2.4501
Epoch 657/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3304 - mean_absolute_error: 0.4068 - val_loss: 10.0513 - val_mean_absolute_error: 2.4106
Epoch 658/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2634 - mean_absolute_error: 0.3486 - val_loss: 10.3552 - val_mean_absolute_error: 2.3897
Epoch 659/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2111 - mean_absolute_error: 0.3181 - val_loss: 10.8019 - val_mean_absolute_error: 2.4729
Epoch 660/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1923 - mean_absolute_error: 0.2727 - val_loss: 10.6068 - val_mean_absolute_error: 2.4397
Epoch 661/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2085 - mean_absolute_error: 0.2779 - val_loss: 10.3626 - val_mean_absolute_error: 2.4328
Epoch 662/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1972 - mean_absolute_error: 0.2866 - val_loss: 9.9571 - val_mean_absolute_error: 2.3805
Epoch 663/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2015 - mean_absolute_error: 0.2986 - val_loss: 10.8264 - val_mean_absolute_error: 2.4147
Epoch 664/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2275 - mean_absolute_error: 0.3106 - val_loss: 10.3624 - val_mean_absolute_error: 2.3884
Epoch 665/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2606 - mean_absolute_error: 0.3369 - val_loss: 9.6471 - val_mean_absolute_error: 2.3481
Epoch 666/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2001 - mean_absolute_error: 0.3074 - val_loss: 10.5685 - val_mean_absolute_error: 2.4195
Epoch 667/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2097 - mean_absolute_error: 0.2968 - val_loss: 10.0843 - val_mean_absolute_error: 2.3795
Epoch 668/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1862 - mean_absolute_error: 0.2849 - val_loss: 9.8770 - val_mean_absolute_error: 2.3515
Epoch 669/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1630 - mean_absolute_error: 0.2555 - val_loss: 10.7629 - val_mean_absolute_error: 2.4088
Epoch 670/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1396 - mean_absolute_error: 0.2246 - val_loss: 9.6465 - val_mean_absolute_error: 2.3781
Epoch 671/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1541 - mean_absolute_error: 0.2522 - val_loss: 10.4173 - val_mean_absolute_error: 2.3964
Epoch 672/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1378 - mean_absolute_error: 0.2101 - val_loss: 10.4859 - val_mean_absolute_error: 2.4112
Epoch 673/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1259 - mean_absolute_error: 0.2103 - val_loss: 9.4698 - val_mean_absolute_error: 2.3189
Epoch 674/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1466 - mean_absolute_error: 0.2212 - val_loss: 10.2490 - val_mean_absolute_error: 2.3638
Epoch 675/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1357 - mean_absolute_error: 0.2169 - val_loss: 10.1685 - val_mean_absolute_error: 2.3847
Epoch 676/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.1263 - mean_absolute_error: 0.1880 - val_loss: 9.7661 - val_mean_absolute_error: 2.3544
Epoch 677/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1240 - mean_absolute_error: 0.2107 - val_loss: 10.6475 - val_mean_absolute_error: 2.3833
Epoch 678/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1245 - mean_absolute_error: 0.2098 - val_loss: 10.4232 - val_mean_absolute_error: 2.3969
Epoch 679/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1181 - mean_absolute_error: 0.1851 - val_loss: 9.8330 - val_mean_absolute_error: 2.3689
Epoch 680/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1000 - mean_absolute_error: 0.1617 - val_loss: 10.5502 - val_mean_absolute_error: 2.3856
Epoch 681/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1030 - mean_absolute_error: 0.1663 - val_loss: 10.0333 - val_mean_absolute_error: 2.3564
Epoch 682/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.1080 - mean_absolute_error: 0.1588 - val_loss: 10.0682 - val_mean_absolute_error: 2.3648
Epoch 683/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0954 - mean_absolute_error: 0.1496 - val_loss: 10.0174 - val_mean_absolute_error: 2.3649
Epoch 684/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0930 - mean_absolute_error: 0.1432 - val_loss: 10.2386 - val_mean_absolute_error: 2.3642
Epoch 685/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0916 - mean_absolute_error: 0.1405 - val_loss: 10.0398 - val_mean_absolute_error: 2.3894
Epoch 686/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0995 - mean_absolute_error: 0.1569 - val_loss: 10.1684 - val_mean_absolute_error: 2.3801
Epoch 687/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0981 - mean_absolute_error: 0.1582 - val_loss: 10.1447 - val_mean_absolute_error: 2.3536
Epoch 688/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1108 - mean_absolute_error: 0.1573 - val_loss: 10.1180 - val_mean_absolute_error: 2.3867
Epoch 689/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3149 - mean_absolute_error: 0.2487 - val_loss: 10.3141 - val_mean_absolute_error: 2.4067
Epoch 690/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3092 - mean_absolute_error: 0.3132 - val_loss: 10.3149 - val_mean_absolute_error: 2.3917
Epoch 691/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2296 - mean_absolute_error: 0.2840 - val_loss: 9.9770 - val_mean_absolute_error: 2.3760
Epoch 692/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.1959 - mean_absolute_error: 0.2604 - val_loss: 10.4639 - val_mean_absolute_error: 2.4171
Epoch 693/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2162 - mean_absolute_error: 0.2454 - val_loss: 10.2767 - val_mean_absolute_error: 2.3839
Epoch 694/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2329 - mean_absolute_error: 0.2165 - val_loss: 10.0977 - val_mean_absolute_error: 2.3726
Epoch 695/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3742 - mean_absolute_error: 0.3292 - val_loss: 10.4222 - val_mean_absolute_error: 2.4023
Epoch 696/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3038 - mean_absolute_error: 0.3109 - val_loss: 10.6402 - val_mean_absolute_error: 2.4402
Epoch 697/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2280 - mean_absolute_error: 0.2921 - val_loss: 10.2871 - val_mean_absolute_error: 2.3743
Epoch 698/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2142 - mean_absolute_error: 0.2953 - val_loss: 10.2056 - val_mean_absolute_error: 2.3774
Epoch 699/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.1938 - mean_absolute_error: 0.2726 - val_loss: 9.7663 - val_mean_absolute_error: 2.3246
Epoch 700/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1929 - mean_absolute_error: 0.2812 - val_loss: 10.4878 - val_mean_absolute_error: 2.4089
Epoch 701/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1512 - mean_absolute_error: 0.2428 - val_loss: 10.7732 - val_mean_absolute_error: 2.4132
Epoch 702/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.2268 - mean_absolute_error: 0.2616 - val_loss: 9.6834 - val_mean_absolute_error: 2.3762
Epoch 703/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.2670 - mean_absolute_error: 0.3151 - val_loss: 10.3504 - val_mean_absolute_error: 2.3488
Epoch 704/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.1960 - mean_absolute_error: 0.2540 - val_loss: 10.3162 - val_mean_absolute_error: 2.3315
Epoch 705/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1811 - mean_absolute_error: 0.2568 - val_loss: 10.2779 - val_mean_absolute_error: 2.3721
Epoch 706/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1495 - mean_absolute_error: 0.2111 - val_loss: 10.0691 - val_mean_absolute_error: 2.4064
Epoch 707/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1670 - mean_absolute_error: 0.2372 - val_loss: 10.1739 - val_mean_absolute_error: 2.3739
Epoch 708/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1309 - mean_absolute_error: 0.1953 - val_loss: 10.5435 - val_mean_absolute_error: 2.3710
Epoch 709/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1382 - mean_absolute_error: 0.2115 - val_loss: 10.0229 - val_mean_absolute_error: 2.3694
Epoch 710/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1548 - mean_absolute_error: 0.2269 - val_loss: 10.0693 - val_mean_absolute_error: 2.3937
Epoch 711/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1407 - mean_absolute_error: 0.2196 - val_loss: 11.1673 - val_mean_absolute_error: 2.4491
Epoch 712/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1385 - mean_absolute_error: 0.2244 - val_loss: 10.1632 - val_mean_absolute_error: 2.3715
Epoch 713/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1600 - mean_absolute_error: 0.2175 - val_loss: 10.1589 - val_mean_absolute_error: 2.3583
Epoch 714/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1636 - mean_absolute_error: 0.1941 - val_loss: 10.5111 - val_mean_absolute_error: 2.3725
Epoch 715/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1673 - mean_absolute_error: 0.2592 - val_loss: 10.2272 - val_mean_absolute_error: 2.4079
Epoch 716/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2026 - mean_absolute_error: 0.2671 - val_loss: 11.0365 - val_mean_absolute_error: 2.4620
Epoch 717/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1793 - mean_absolute_error: 0.2399 - val_loss: 10.1342 - val_mean_absolute_error: 2.3640
Epoch 718/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1429 - mean_absolute_error: 0.2109 - val_loss: 10.2653 - val_mean_absolute_error: 2.3329
Epoch 719/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1371 - mean_absolute_error: 0.2032 - val_loss: 10.1968 - val_mean_absolute_error: 2.3440
Epoch 720/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1251 - mean_absolute_error: 0.1832 - val_loss: 10.1238 - val_mean_absolute_error: 2.3591
Epoch 721/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1057 - mean_absolute_error: 0.1567 - val_loss: 10.3474 - val_mean_absolute_error: 2.3737
Epoch 722/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1068 - mean_absolute_error: 0.1594 - val_loss: 10.4411 - val_mean_absolute_error: 2.3631
Epoch 723/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1068 - mean_absolute_error: 0.1714 - val_loss: 10.3184 - val_mean_absolute_error: 2.3704
Epoch 724/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1304 - mean_absolute_error: 0.1971 - val_loss: 9.8914 - val_mean_absolute_error: 2.3762
Epoch 725/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2186 - mean_absolute_error: 0.2429 - val_loss: 10.3915 - val_mean_absolute_error: 2.3644
Epoch 726/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1849 - mean_absolute_error: 0.2211 - val_loss: 10.4496 - val_mean_absolute_error: 2.3643
Epoch 727/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1430 - mean_absolute_error: 0.2054 - val_loss: 10.0562 - val_mean_absolute_error: 2.3312
Epoch 728/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1271 - mean_absolute_error: 0.1913 - val_loss: 10.2529 - val_mean_absolute_error: 2.3881
Epoch 729/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1202 - mean_absolute_error: 0.1610 - val_loss: 10.3018 - val_mean_absolute_error: 2.3849
Epoch 730/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1030 - mean_absolute_error: 0.1573 - val_loss: 10.1353 - val_mean_absolute_error: 2.3565
Epoch 731/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.1186 - mean_absolute_error: 0.1531 - val_loss: 10.2065 - val_mean_absolute_error: 2.3875
Epoch 732/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1111 - mean_absolute_error: 0.1482 - val_loss: 10.2270 - val_mean_absolute_error: 2.3761
Epoch 733/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1164 - mean_absolute_error: 0.1675 - val_loss: 10.0196 - val_mean_absolute_error: 2.3282
Epoch 734/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1450 - mean_absolute_error: 0.1927 - val_loss: 10.2741 - val_mean_absolute_error: 2.3600
Epoch 735/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1167 - mean_absolute_error: 0.1967 - val_loss: 10.0381 - val_mean_absolute_error: 2.3566
Epoch 736/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1177 - mean_absolute_error: 0.1931 - val_loss: 10.1790 - val_mean_absolute_error: 2.3810
Epoch 737/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1054 - mean_absolute_error: 0.1890 - val_loss: 10.3172 - val_mean_absolute_error: 2.3857
Epoch 738/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.0911 - mean_absolute_error: 0.1850 - val_loss: 10.2035 - val_mean_absolute_error: 2.3678
Epoch 739/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.0908 - mean_absolute_error: 0.1654 - val_loss: 10.1017 - val_mean_absolute_error: 2.3679
Epoch 740/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0783 - mean_absolute_error: 0.1567 - val_loss: 10.4459 - val_mean_absolute_error: 2.4033
Epoch 741/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0839 - mean_absolute_error: 0.1645 - val_loss: 10.5000 - val_mean_absolute_error: 2.3715
Epoch 742/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1059 - mean_absolute_error: 0.1807 - val_loss: 9.8059 - val_mean_absolute_error: 2.3921
Epoch 743/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0932 - mean_absolute_error: 0.1788 - val_loss: 10.0581 - val_mean_absolute_error: 2.3499
Epoch 744/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0944 - mean_absolute_error: 0.1767 - val_loss: 10.6674 - val_mean_absolute_error: 2.4088
Epoch 745/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1146 - mean_absolute_error: 0.1852 - val_loss: 10.1211 - val_mean_absolute_error: 2.3637
Epoch 746/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1269 - mean_absolute_error: 0.2060 - val_loss: 9.8502 - val_mean_absolute_error: 2.3593
Epoch 747/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1324 - mean_absolute_error: 0.2045 - val_loss: 10.7470 - val_mean_absolute_error: 2.4097
Epoch 748/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2082 - mean_absolute_error: 0.2335 - val_loss: 9.8711 - val_mean_absolute_error: 2.3177
Epoch 749/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1695 - mean_absolute_error: 0.2125 - val_loss: 10.3527 - val_mean_absolute_error: 2.3901
Epoch 750/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1402 - mean_absolute_error: 0.1774 - val_loss: 9.7843 - val_mean_absolute_error: 2.3359
Epoch 751/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1386 - mean_absolute_error: 0.1941 - val_loss: 10.1375 - val_mean_absolute_error: 2.3344
Epoch 752/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1037 - mean_absolute_error: 0.1642 - val_loss: 10.0714 - val_mean_absolute_error: 2.3372
Epoch 753/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0891 - mean_absolute_error: 0.1605 - val_loss: 10.0470 - val_mean_absolute_error: 2.3392
Epoch 754/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0893 - mean_absolute_error: 0.1552 - val_loss: 9.9866 - val_mean_absolute_error: 2.3521
Epoch 755/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2176 - mean_absolute_error: 0.2481 - val_loss: 10.4790 - val_mean_absolute_error: 2.3940
Epoch 756/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3476 - mean_absolute_error: 0.2930 - val_loss: 10.2879 - val_mean_absolute_error: 2.4231
Epoch 757/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2820 - mean_absolute_error: 0.3194 - val_loss: 9.9936 - val_mean_absolute_error: 2.3279
Epoch 758/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2459 - mean_absolute_error: 0.2971 - val_loss: 9.9874 - val_mean_absolute_error: 2.3077
Epoch 759/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1752 - mean_absolute_error: 0.2521 - val_loss: 10.1942 - val_mean_absolute_error: 2.3544
Epoch 760/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1574 - mean_absolute_error: 0.2332 - val_loss: 9.6953 - val_mean_absolute_error: 2.3219
Epoch 761/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1376 - mean_absolute_error: 0.1922 - val_loss: 9.9198 - val_mean_absolute_error: 2.3168
Epoch 762/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1222 - mean_absolute_error: 0.1818 - val_loss: 9.9291 - val_mean_absolute_error: 2.3207
Epoch 763/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1220 - mean_absolute_error: 0.1706 - val_loss: 10.1213 - val_mean_absolute_error: 2.3459
Epoch 764/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1481 - mean_absolute_error: 0.1754 - val_loss: 10.1768 - val_mean_absolute_error: 2.3286
Epoch 765/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1538 - mean_absolute_error: 0.2153 - val_loss: 9.7376 - val_mean_absolute_error: 2.3309
Epoch 766/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1675 - mean_absolute_error: 0.2572 - val_loss: 10.6375 - val_mean_absolute_error: 2.3984
Epoch 767/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1542 - mean_absolute_error: 0.2480 - val_loss: 10.2450 - val_mean_absolute_error: 2.3260
Epoch 768/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1767 - mean_absolute_error: 0.2785 - val_loss: 9.8988 - val_mean_absolute_error: 2.3135
Epoch 769/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1992 - mean_absolute_error: 0.2906 - val_loss: 10.0714 - val_mean_absolute_error: 2.3734
Epoch 770/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3856 - mean_absolute_error: 0.3676 - val_loss: 10.2363 - val_mean_absolute_error: 2.3879
Epoch 771/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2177 - mean_absolute_error: 0.3136 - val_loss: 10.4639 - val_mean_absolute_error: 2.3518
Epoch 772/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2586 - mean_absolute_error: 0.3183 - val_loss: 9.8275 - val_mean_absolute_error: 2.3146
Epoch 773/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1822 - mean_absolute_error: 0.2783 - val_loss: 9.6529 - val_mean_absolute_error: 2.3076
Epoch 774/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2057 - mean_absolute_error: 0.2944 - val_loss: 9.9646 - val_mean_absolute_error: 2.3496
Epoch 775/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1597 - mean_absolute_error: 0.2465 - val_loss: 10.4967 - val_mean_absolute_error: 2.3726
Epoch 776/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1544 - mean_absolute_error: 0.2298 - val_loss: 10.2042 - val_mean_absolute_error: 2.3717
Epoch 777/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1755 - mean_absolute_error: 0.2678 - val_loss: 10.0374 - val_mean_absolute_error: 2.3614
Epoch 778/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1431 - mean_absolute_error: 0.2366 - val_loss: 10.2364 - val_mean_absolute_error: 2.3751
Epoch 779/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1126 - mean_absolute_error: 0.1816 - val_loss: 10.0905 - val_mean_absolute_error: 2.3180
Epoch 780/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.1308 - mean_absolute_error: 0.2003 - val_loss: 9.7113 - val_mean_absolute_error: 2.3175
Epoch 781/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1075 - mean_absolute_error: 0.1850 - val_loss: 9.8982 - val_mean_absolute_error: 2.3344
Epoch 782/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1231 - mean_absolute_error: 0.2023 - val_loss: 10.0303 - val_mean_absolute_error: 2.3449
Epoch 783/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1640 - mean_absolute_error: 0.2351 - val_loss: 9.9323 - val_mean_absolute_error: 2.3505
Epoch 784/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1210 - mean_absolute_error: 0.1924 - val_loss: 10.2971 - val_mean_absolute_error: 2.3482
Epoch 785/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1157 - mean_absolute_error: 0.1966 - val_loss: 9.5108 - val_mean_absolute_error: 2.3066
Epoch 786/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1280 - mean_absolute_error: 0.2126 - val_loss: 10.2425 - val_mean_absolute_error: 2.3530
Epoch 787/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1564 - mean_absolute_error: 0.2345 - val_loss: 9.9248 - val_mean_absolute_error: 2.3703
Epoch 788/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1594 - mean_absolute_error: 0.2172 - val_loss: 10.0815 - val_mean_absolute_error: 2.3483
Epoch 789/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1717 - mean_absolute_error: 0.2609 - val_loss: 9.6467 - val_mean_absolute_error: 2.3185
Epoch 790/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1417 - mean_absolute_error: 0.2485 - val_loss: 10.0133 - val_mean_absolute_error: 2.3468
Epoch 791/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1494 - mean_absolute_error: 0.2410 - val_loss: 10.1566 - val_mean_absolute_error: 2.3588
Epoch 792/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1818 - mean_absolute_error: 0.2352 - val_loss: 9.9178 - val_mean_absolute_error: 2.3294
Epoch 793/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1675 - mean_absolute_error: 0.2244 - val_loss: 9.8559 - val_mean_absolute_error: 2.3569
Epoch 794/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2377 - mean_absolute_error: 0.2747 - val_loss: 9.9941 - val_mean_absolute_error: 2.3525
Epoch 795/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2328 - mean_absolute_error: 0.2644 - val_loss: 10.2322 - val_mean_absolute_error: 2.4078
Epoch 796/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1659 - mean_absolute_error: 0.2275 - val_loss: 9.9292 - val_mean_absolute_error: 2.3613
Epoch 797/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1353 - mean_absolute_error: 0.2140 - val_loss: 9.7356 - val_mean_absolute_error: 2.3040
Epoch 798/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1411 - mean_absolute_error: 0.2160 - val_loss: 9.3820 - val_mean_absolute_error: 2.2865
Epoch 799/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1434 - mean_absolute_error: 0.2339 - val_loss: 10.0685 - val_mean_absolute_error: 2.3594
Epoch 800/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1796 - mean_absolute_error: 0.2853 - val_loss: 9.7468 - val_mean_absolute_error: 2.2655
Epoch 801/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1827 - mean_absolute_error: 0.2989 - val_loss: 9.8847 - val_mean_absolute_error: 2.3070
Epoch 802/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1518 - mean_absolute_error: 0.2527 - val_loss: 9.8165 - val_mean_absolute_error: 2.3520
Epoch 803/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1761 - mean_absolute_error: 0.2691 - val_loss: 10.6228 - val_mean_absolute_error: 2.3619
Epoch 804/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1706 - mean_absolute_error: 0.2865 - val_loss: 9.4497 - val_mean_absolute_error: 2.3268
Epoch 805/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1544 - mean_absolute_error: 0.2599 - val_loss: 10.1216 - val_mean_absolute_error: 2.3904
Epoch 806/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1306 - mean_absolute_error: 0.2277 - val_loss: 9.5613 - val_mean_absolute_error: 2.2801
Epoch 807/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1565 - mean_absolute_error: 0.2510 - val_loss: 9.6277 - val_mean_absolute_error: 2.2809
Epoch 808/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1260 - mean_absolute_error: 0.2273 - val_loss: 10.1417 - val_mean_absolute_error: 2.3427
Epoch 809/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1157 - mean_absolute_error: 0.2087 - val_loss: 10.2753 - val_mean_absolute_error: 2.3365
Epoch 810/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.0962 - mean_absolute_error: 0.1809 - val_loss: 9.9123 - val_mean_absolute_error: 2.3645
Epoch 811/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1104 - mean_absolute_error: 0.1963 - val_loss: 9.5100 - val_mean_absolute_error: 2.3381
Epoch 812/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1136 - mean_absolute_error: 0.2277 - val_loss: 10.0335 - val_mean_absolute_error: 2.3548
Epoch 813/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1042 - mean_absolute_error: 0.2081 - val_loss: 10.2245 - val_mean_absolute_error: 2.3471
Epoch 814/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1149 - mean_absolute_error: 0.2170 - val_loss: 10.0038 - val_mean_absolute_error: 2.3421
Epoch 815/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1114 - mean_absolute_error: 0.2101 - val_loss: 9.9335 - val_mean_absolute_error: 2.3978
Epoch 816/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1072 - mean_absolute_error: 0.1900 - val_loss: 9.7490 - val_mean_absolute_error: 2.3276
Epoch 817/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1121 - mean_absolute_error: 0.1919 - val_loss: 9.8989 - val_mean_absolute_error: 2.3103
Epoch 818/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1305 - mean_absolute_error: 0.1966 - val_loss: 9.4392 - val_mean_absolute_error: 2.3313
Epoch 819/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1015 - mean_absolute_error: 0.2153 - val_loss: 9.7320 - val_mean_absolute_error: 2.3160
Epoch 820/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1119 - mean_absolute_error: 0.2018 - val_loss: 10.1481 - val_mean_absolute_error: 2.3213
Epoch 821/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1543 - mean_absolute_error: 0.2713 - val_loss: 9.8805 - val_mean_absolute_error: 2.3441
Epoch 822/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1490 - mean_absolute_error: 0.2520 - val_loss: 9.8380 - val_mean_absolute_error: 2.3566
Epoch 823/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1360 - mean_absolute_error: 0.2458 - val_loss: 10.0785 - val_mean_absolute_error: 2.3512
Epoch 824/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1714 - mean_absolute_error: 0.2554 - val_loss: 10.4272 - val_mean_absolute_error: 2.3674
Epoch 825/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1925 - mean_absolute_error: 0.2646 - val_loss: 9.6842 - val_mean_absolute_error: 2.3379
Epoch 826/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2804 - mean_absolute_error: 0.3053 - val_loss: 10.2486 - val_mean_absolute_error: 2.4644
Epoch 827/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2414 - mean_absolute_error: 0.3385 - val_loss: 10.6779 - val_mean_absolute_error: 2.3790
Epoch 828/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2292 - mean_absolute_error: 0.3373 - val_loss: 8.5862 - val_mean_absolute_error: 2.2413
Epoch 829/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.2418 - mean_absolute_error: 0.3153 - val_loss: 9.1988 - val_mean_absolute_error: 2.2596
Epoch 830/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3548 - mean_absolute_error: 0.3577 - val_loss: 10.0992 - val_mean_absolute_error: 2.3987
Epoch 831/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2333 - mean_absolute_error: 0.3435 - val_loss: 9.3266 - val_mean_absolute_error: 2.2870
Epoch 832/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2799 - mean_absolute_error: 0.3629 - val_loss: 8.8915 - val_mean_absolute_error: 2.2136
Epoch 833/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3545 - mean_absolute_error: 0.4474 - val_loss: 9.6896 - val_mean_absolute_error: 2.2284
Epoch 834/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.2580 - mean_absolute_error: 0.3870 - val_loss: 9.4169 - val_mean_absolute_error: 2.3404
Epoch 835/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.2539 - mean_absolute_error: 0.3706 - val_loss: 9.7283 - val_mean_absolute_error: 2.3361
Epoch 836/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.2156 - mean_absolute_error: 0.3128 - val_loss: 9.7134 - val_mean_absolute_error: 2.2836
Epoch 837/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.2464 - mean_absolute_error: 0.3475 - val_loss: 9.3315 - val_mean_absolute_error: 2.2975
Epoch 838/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.4040 - mean_absolute_error: 0.3930 - val_loss: 10.1315 - val_mean_absolute_error: 2.3800
Epoch 839/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3585 - mean_absolute_error: 0.3707 - val_loss: 9.1701 - val_mean_absolute_error: 2.2536
Epoch 840/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2135 - mean_absolute_error: 0.3105 - val_loss: 10.1400 - val_mean_absolute_error: 2.3480
Epoch 841/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.2204 - mean_absolute_error: 0.2947 - val_loss: 9.9063 - val_mean_absolute_error: 2.3540
Epoch 842/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3301 - mean_absolute_error: 0.3574 - val_loss: 8.7144 - val_mean_absolute_error: 2.2200
Epoch 843/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2444 - mean_absolute_error: 0.3541 - val_loss: 10.3508 - val_mean_absolute_error: 2.3409
Epoch 844/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2944 - mean_absolute_error: 0.4098 - val_loss: 9.7678 - val_mean_absolute_error: 2.3438
Epoch 845/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2759 - mean_absolute_error: 0.3997 - val_loss: 9.2358 - val_mean_absolute_error: 2.3273
Epoch 846/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2871 - mean_absolute_error: 0.3923 - val_loss: 9.8554 - val_mean_absolute_error: 2.3850
Epoch 847/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2234 - mean_absolute_error: 0.3646 - val_loss: 11.3354 - val_mean_absolute_error: 2.4403
Epoch 848/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2557 - mean_absolute_error: 0.3590 - val_loss: 9.3213 - val_mean_absolute_error: 2.3117
Epoch 849/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1465 - mean_absolute_error: 0.2803 - val_loss: 10.3101 - val_mean_absolute_error: 2.3573
Epoch 850/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1910 - mean_absolute_error: 0.2817 - val_loss: 9.9576 - val_mean_absolute_error: 2.3201
Epoch 851/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1502 - mean_absolute_error: 0.2887 - val_loss: 9.4299 - val_mean_absolute_error: 2.2701
Epoch 852/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1538 - mean_absolute_error: 0.2563 - val_loss: 9.3733 - val_mean_absolute_error: 2.3229
Epoch 853/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1391 - mean_absolute_error: 0.2442 - val_loss: 10.4008 - val_mean_absolute_error: 2.4038
Epoch 854/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3139 - mean_absolute_error: 0.2416 - val_loss: 9.4604 - val_mean_absolute_error: 2.3110
Epoch 855/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2701 - mean_absolute_error: 0.2492 - val_loss: 9.3546 - val_mean_absolute_error: 2.2727
Epoch 856/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1949 - mean_absolute_error: 0.2623 - val_loss: 10.3103 - val_mean_absolute_error: 2.3582
Epoch 857/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1651 - mean_absolute_error: 0.2506 - val_loss: 9.5093 - val_mean_absolute_error: 2.3721
Epoch 858/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1723 - mean_absolute_error: 0.2719 - val_loss: 10.1541 - val_mean_absolute_error: 2.3332
Epoch 859/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1501 - mean_absolute_error: 0.2499 - val_loss: 10.1119 - val_mean_absolute_error: 2.3665
Epoch 860/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1354 - mean_absolute_error: 0.2284 - val_loss: 9.6314 - val_mean_absolute_error: 2.3668
Epoch 861/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1342 - mean_absolute_error: 0.2424 - val_loss: 9.9307 - val_mean_absolute_error: 2.3339
Epoch 862/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1387 - mean_absolute_error: 0.2246 - val_loss: 10.0994 - val_mean_absolute_error: 2.3609
Epoch 863/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1182 - mean_absolute_error: 0.2163 - val_loss: 9.3258 - val_mean_absolute_error: 2.3695
Epoch 864/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1108 - mean_absolute_error: 0.2034 - val_loss: 10.0268 - val_mean_absolute_error: 2.3638
Epoch 865/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0789 - mean_absolute_error: 0.1788 - val_loss: 9.5128 - val_mean_absolute_error: 2.3130
Epoch 866/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0873 - mean_absolute_error: 0.1648 - val_loss: 9.6141 - val_mean_absolute_error: 2.3174
Epoch 867/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0690 - mean_absolute_error: 0.1504 - val_loss: 9.9993 - val_mean_absolute_error: 2.3406
Epoch 868/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0810 - mean_absolute_error: 0.1553 - val_loss: 9.8029 - val_mean_absolute_error: 2.3509
Epoch 869/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0708 - mean_absolute_error: 0.1487 - val_loss: 9.9710 - val_mean_absolute_error: 2.3374
Epoch 870/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0595 - mean_absolute_error: 0.1439 - val_loss: 9.6536 - val_mean_absolute_error: 2.3266
Epoch 871/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0636 - mean_absolute_error: 0.1438 - val_loss: 9.5346 - val_mean_absolute_error: 2.3164
Epoch 872/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0962 - mean_absolute_error: 0.1683 - val_loss: 10.0575 - val_mean_absolute_error: 2.3494
Epoch 873/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0813 - mean_absolute_error: 0.1859 - val_loss: 9.4436 - val_mean_absolute_error: 2.3205
Epoch 874/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0956 - mean_absolute_error: 0.1613 - val_loss: 9.6993 - val_mean_absolute_error: 2.3077
Epoch 875/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4677 - mean_absolute_error: 0.3047 - val_loss: 9.7181 - val_mean_absolute_error: 2.3715
Epoch 876/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4813 - mean_absolute_error: 0.3411 - val_loss: 10.2577 - val_mean_absolute_error: 2.4307
Epoch 877/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3378 - mean_absolute_error: 0.3015 - val_loss: 9.7158 - val_mean_absolute_error: 2.2873
Epoch 878/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.2456 - mean_absolute_error: 0.2787 - val_loss: 9.6724 - val_mean_absolute_error: 2.2595
Epoch 879/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2001 - mean_absolute_error: 0.2526 - val_loss: 9.6855 - val_mean_absolute_error: 2.3293
Epoch 880/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1872 - mean_absolute_error: 0.2416 - val_loss: 9.8330 - val_mean_absolute_error: 2.3284
Epoch 881/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1501 - mean_absolute_error: 0.2066 - val_loss: 9.8352 - val_mean_absolute_error: 2.2861
Epoch 882/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1684 - mean_absolute_error: 0.2434 - val_loss: 9.5601 - val_mean_absolute_error: 2.3026
Epoch 883/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1359 - mean_absolute_error: 0.2115 - val_loss: 9.5208 - val_mean_absolute_error: 2.2859
Epoch 884/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1447 - mean_absolute_error: 0.1950 - val_loss: 9.6063 - val_mean_absolute_error: 2.2949
Epoch 885/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1250 - mean_absolute_error: 0.1846 - val_loss: 9.4987 - val_mean_absolute_error: 2.2974
Epoch 886/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1503 - mean_absolute_error: 0.1909 - val_loss: 9.9596 - val_mean_absolute_error: 2.3278
Epoch 887/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1098 - mean_absolute_error: 0.1732 - val_loss: 9.5967 - val_mean_absolute_error: 2.3080
Epoch 888/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1763 - mean_absolute_error: 0.1954 - val_loss: 9.8019 - val_mean_absolute_error: 2.2949
Epoch 889/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1607 - mean_absolute_error: 0.2124 - val_loss: 9.7368 - val_mean_absolute_error: 2.3342
Epoch 890/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1378 - mean_absolute_error: 0.2019 - val_loss: 9.9137 - val_mean_absolute_error: 2.3219
Epoch 891/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1505 - mean_absolute_error: 0.2193 - val_loss: 9.6684 - val_mean_absolute_error: 2.3083
Epoch 892/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1329 - mean_absolute_error: 0.1769 - val_loss: 9.5989 - val_mean_absolute_error: 2.3047
Epoch 893/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1562 - mean_absolute_error: 0.1952 - val_loss: 9.8837 - val_mean_absolute_error: 2.3443
Epoch 894/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1442 - mean_absolute_error: 0.2226 - val_loss: 9.7905 - val_mean_absolute_error: 2.3144
Epoch 895/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1664 - mean_absolute_error: 0.2747 - val_loss: 9.5331 - val_mean_absolute_error: 2.3190
Epoch 896/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1580 - mean_absolute_error: 0.2662 - val_loss: 10.1353 - val_mean_absolute_error: 2.3363
Epoch 897/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1324 - mean_absolute_error: 0.2448 - val_loss: 9.7743 - val_mean_absolute_error: 2.3231
Epoch 898/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1143 - mean_absolute_error: 0.2107 - val_loss: 9.6280 - val_mean_absolute_error: 2.3495
Epoch 899/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0972 - mean_absolute_error: 0.1813 - val_loss: 10.0769 - val_mean_absolute_error: 2.3549
Epoch 900/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.0946 - mean_absolute_error: 0.1567 - val_loss: 9.7088 - val_mean_absolute_error: 2.3346
Epoch 901/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2574 - mean_absolute_error: 0.2255 - val_loss: 9.3434 - val_mean_absolute_error: 2.2547
Epoch 902/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1657 - mean_absolute_error: 0.2624 - val_loss: 9.7276 - val_mean_absolute_error: 2.3440
Epoch 903/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1576 - mean_absolute_error: 0.2349 - val_loss: 10.2963 - val_mean_absolute_error: 2.3473
Epoch 904/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1352 - mean_absolute_error: 0.2278 - val_loss: 9.7690 - val_mean_absolute_error: 2.2699
Epoch 905/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1598 - mean_absolute_error: 0.2293 - val_loss: 9.0848 - val_mean_absolute_error: 2.2516
Epoch 906/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1477 - mean_absolute_error: 0.2585 - val_loss: 10.1780 - val_mean_absolute_error: 2.3617
Epoch 907/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1787 - mean_absolute_error: 0.2844 - val_loss: 9.9149 - val_mean_absolute_error: 2.3522
Epoch 908/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1790 - mean_absolute_error: 0.2759 - val_loss: 9.6591 - val_mean_absolute_error: 2.3326
Epoch 909/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1619 - mean_absolute_error: 0.2699 - val_loss: 10.2246 - val_mean_absolute_error: 2.3648
Epoch 910/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1535 - mean_absolute_error: 0.2477 - val_loss: 10.3153 - val_mean_absolute_error: 2.3867
Epoch 911/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1315 - mean_absolute_error: 0.2484 - val_loss: 9.5141 - val_mean_absolute_error: 2.3040
Epoch 912/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1155 - mean_absolute_error: 0.2250 - val_loss: 10.0245 - val_mean_absolute_error: 2.3195
Epoch 913/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1115 - mean_absolute_error: 0.1950 - val_loss: 9.9850 - val_mean_absolute_error: 2.3281
Epoch 914/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1930 - mean_absolute_error: 0.2165 - val_loss: 9.8310 - val_mean_absolute_error: 2.3283
Epoch 915/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2216 - mean_absolute_error: 0.2180 - val_loss: 10.2999 - val_mean_absolute_error: 2.3915
Epoch 916/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1203 - mean_absolute_error: 0.2283 - val_loss: 9.7901 - val_mean_absolute_error: 2.3422
Epoch 917/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1480 - mean_absolute_error: 0.2428 - val_loss: 9.8438 - val_mean_absolute_error: 2.3091
Epoch 918/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1283 - mean_absolute_error: 0.2280 - val_loss: 9.8470 - val_mean_absolute_error: 2.3292
Epoch 919/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2210 - mean_absolute_error: 0.2639 - val_loss: 9.9021 - val_mean_absolute_error: 2.3081
Epoch 920/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1515 - mean_absolute_error: 0.2295 - val_loss: 9.3645 - val_mean_absolute_error: 2.2721
Epoch 921/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1048 - mean_absolute_error: 0.1951 - val_loss: 10.1572 - val_mean_absolute_error: 2.3445
Epoch 922/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0983 - mean_absolute_error: 0.1913 - val_loss: 9.7456 - val_mean_absolute_error: 2.3347
Epoch 923/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0924 - mean_absolute_error: 0.1704 - val_loss: 9.5136 - val_mean_absolute_error: 2.2934
Epoch 924/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0834 - mean_absolute_error: 0.1837 - val_loss: 10.1246 - val_mean_absolute_error: 2.3393
Epoch 925/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0879 - mean_absolute_error: 0.1809 - val_loss: 9.9775 - val_mean_absolute_error: 2.3647
Epoch 926/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0991 - mean_absolute_error: 0.1876 - val_loss: 9.7849 - val_mean_absolute_error: 2.3499
Epoch 927/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1398 - mean_absolute_error: 0.2128 - val_loss: 9.8738 - val_mean_absolute_error: 2.3446
Epoch 928/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1016 - mean_absolute_error: 0.2139 - val_loss: 9.6806 - val_mean_absolute_error: 2.3450
Epoch 929/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1025 - mean_absolute_error: 0.2164 - val_loss: 9.6901 - val_mean_absolute_error: 2.3454
Epoch 930/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.0799 - mean_absolute_error: 0.1813 - val_loss: 10.2182 - val_mean_absolute_error: 2.3743
Epoch 931/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0768 - mean_absolute_error: 0.1816 - val_loss: 9.6026 - val_mean_absolute_error: 2.3305
Epoch 932/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.0883 - mean_absolute_error: 0.1591 - val_loss: 10.0524 - val_mean_absolute_error: 2.3673
Epoch 933/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.3199 - mean_absolute_error: 0.2548 - val_loss: 10.3891 - val_mean_absolute_error: 2.3891
Epoch 934/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2671 - mean_absolute_error: 0.2702 - val_loss: 9.1466 - val_mean_absolute_error: 2.2509
Epoch 935/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2032 - mean_absolute_error: 0.2722 - val_loss: 9.3928 - val_mean_absolute_error: 2.3009
Epoch 936/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1280 - mean_absolute_error: 0.2277 - val_loss: 10.1636 - val_mean_absolute_error: 2.3963
Epoch 937/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1196 - mean_absolute_error: 0.2216 - val_loss: 9.5919 - val_mean_absolute_error: 2.3296
Epoch 938/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1226 - mean_absolute_error: 0.2067 - val_loss: 9.8833 - val_mean_absolute_error: 2.3222
Epoch 939/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1103 - mean_absolute_error: 0.1967 - val_loss: 9.4949 - val_mean_absolute_error: 2.3214
Epoch 940/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0992 - mean_absolute_error: 0.1971 - val_loss: 9.6950 - val_mean_absolute_error: 2.3582
Epoch 941/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1016 - mean_absolute_error: 0.1958 - val_loss: 9.6778 - val_mean_absolute_error: 2.3505
Epoch 942/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0986 - mean_absolute_error: 0.1943 - val_loss: 9.7313 - val_mean_absolute_error: 2.3410
Epoch 943/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0724 - mean_absolute_error: 0.1639 - val_loss: 9.6356 - val_mean_absolute_error: 2.3386
Epoch 944/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0732 - mean_absolute_error: 0.1514 - val_loss: 9.7912 - val_mean_absolute_error: 2.3458
Epoch 945/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0855 - mean_absolute_error: 0.1535 - val_loss: 9.5431 - val_mean_absolute_error: 2.3308
Epoch 946/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0741 - mean_absolute_error: 0.1538 - val_loss: 9.6642 - val_mean_absolute_error: 2.3480
Epoch 947/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0939 - mean_absolute_error: 0.1620 - val_loss: 9.9339 - val_mean_absolute_error: 2.3484
Epoch 948/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0776 - mean_absolute_error: 0.1698 - val_loss: 9.7429 - val_mean_absolute_error: 2.3475
Epoch 949/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1244 - mean_absolute_error: 0.1952 - val_loss: 9.4335 - val_mean_absolute_error: 2.3311
Epoch 950/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2951 - mean_absolute_error: 0.2387 - val_loss: 9.6985 - val_mean_absolute_error: 2.3369
Epoch 951/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2142 - mean_absolute_error: 0.2488 - val_loss: 9.5136 - val_mean_absolute_error: 2.3188
Epoch 952/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1614 - mean_absolute_error: 0.2390 - val_loss: 9.5016 - val_mean_absolute_error: 2.3220
Epoch 953/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1372 - mean_absolute_error: 0.2155 - val_loss: 9.6219 - val_mean_absolute_error: 2.3919
Epoch 954/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1003 - mean_absolute_error: 0.2038 - val_loss: 10.2632 - val_mean_absolute_error: 2.4191
Epoch 955/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.1378 - mean_absolute_error: 0.2202 - val_loss: 9.6009 - val_mean_absolute_error: 2.3480
Epoch 956/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0806 - mean_absolute_error: 0.1869 - val_loss: 9.3574 - val_mean_absolute_error: 2.3165
Epoch 957/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0828 - mean_absolute_error: 0.1715 - val_loss: 9.4472 - val_mean_absolute_error: 2.3095
Epoch 958/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0919 - mean_absolute_error: 0.1691 - val_loss: 9.5894 - val_mean_absolute_error: 2.3271
Epoch 959/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0576 - mean_absolute_error: 0.1505 - val_loss: 9.8180 - val_mean_absolute_error: 2.3589
Epoch 960/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0648 - mean_absolute_error: 0.1543 - val_loss: 9.6893 - val_mean_absolute_error: 2.3610
Epoch 961/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0369 - mean_absolute_error: 0.1231 - val_loss: 9.8386 - val_mean_absolute_error: 2.3627
Epoch 962/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.0475 - mean_absolute_error: 0.1234 - val_loss: 9.6366 - val_mean_absolute_error: 2.3278
Epoch 963/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0505 - mean_absolute_error: 0.1343 - val_loss: 9.9482 - val_mean_absolute_error: 2.3666
Epoch 964/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0523 - mean_absolute_error: 0.1354 - val_loss: 9.4746 - val_mean_absolute_error: 2.3289
Epoch 965/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0508 - mean_absolute_error: 0.1361 - val_loss: 9.7156 - val_mean_absolute_error: 2.3592
Epoch 966/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0624 - mean_absolute_error: 0.1583 - val_loss: 9.9157 - val_mean_absolute_error: 2.3661
Epoch 967/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1427 - mean_absolute_error: 0.1952 - val_loss: 10.1382 - val_mean_absolute_error: 2.3890
Epoch 968/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2321 - mean_absolute_error: 0.2482 - val_loss: 9.4973 - val_mean_absolute_error: 2.3290
Epoch 969/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.1582 - mean_absolute_error: 0.2618 - val_loss: 9.6214 - val_mean_absolute_error: 2.3476
Epoch 970/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3159 - mean_absolute_error: 0.3034 - val_loss: 9.8659 - val_mean_absolute_error: 2.4055
Epoch 971/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2633 - mean_absolute_error: 0.3015 - val_loss: 9.3563 - val_mean_absolute_error: 2.3549
Epoch 972/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2277 - mean_absolute_error: 0.2959 - val_loss: 9.6485 - val_mean_absolute_error: 2.3005
Epoch 973/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3695 - mean_absolute_error: 0.3722 - val_loss: 9.3264 - val_mean_absolute_error: 2.3886
Epoch 974/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3100 - mean_absolute_error: 0.3905 - val_loss: 9.9750 - val_mean_absolute_error: 2.3372
Epoch 975/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3895 - mean_absolute_error: 0.4153 - val_loss: 10.0259 - val_mean_absolute_error: 2.3074
Epoch 976/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3406 - mean_absolute_error: 0.4447 - val_loss: 9.7925 - val_mean_absolute_error: 2.3680
Epoch 977/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3946 - mean_absolute_error: 0.4559 - val_loss: 9.4000 - val_mean_absolute_error: 2.3237
Epoch 978/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.3513 - mean_absolute_error: 0.4578 - val_loss: 10.3918 - val_mean_absolute_error: 2.3141
Epoch 979/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.9213 - mean_absolute_error: 0.5757 - val_loss: 8.2951 - val_mean_absolute_error: 2.3032
Epoch 980/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.5378 - mean_absolute_error: 0.4763 - val_loss: 11.3056 - val_mean_absolute_error: 2.2972
Epoch 981/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.6109 - mean_absolute_error: 0.5284 - val_loss: 9.4833 - val_mean_absolute_error: 2.2990
Epoch 982/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.4959 - mean_absolute_error: 0.4951 - val_loss: 9.8858 - val_mean_absolute_error: 2.3354
Epoch 983/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.4903 - mean_absolute_error: 0.5183 - val_loss: 10.2157 - val_mean_absolute_error: 2.3516
Epoch 984/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3702 - mean_absolute_error: 0.4340 - val_loss: 8.7655 - val_mean_absolute_error: 2.3304
Epoch 985/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3843 - mean_absolute_error: 0.4272 - val_loss: 8.9265 - val_mean_absolute_error: 2.1943
Epoch 986/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.1769 - mean_absolute_error: 0.3130 - val_loss: 10.3095 - val_mean_absolute_error: 2.2915
Epoch 987/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2672 - mean_absolute_error: 0.3518 - val_loss: 9.5768 - val_mean_absolute_error: 2.3120
Epoch 988/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1776 - mean_absolute_error: 0.3080 - val_loss: 9.2024 - val_mean_absolute_error: 2.2876
Epoch 989/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1483 - mean_absolute_error: 0.2574 - val_loss: 10.0151 - val_mean_absolute_error: 2.3455
Epoch 990/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0959 - mean_absolute_error: 0.2001 - val_loss: 9.6762 - val_mean_absolute_error: 2.3177
Epoch 991/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1134 - mean_absolute_error: 0.2136 - val_loss: 9.4056 - val_mean_absolute_error: 2.2867
Epoch 992/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0694 - mean_absolute_error: 0.1732 - val_loss: 9.4489 - val_mean_absolute_error: 2.2884
Epoch 993/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1096 - mean_absolute_error: 0.1918 - val_loss: 9.4864 - val_mean_absolute_error: 2.3156
Epoch 994/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0604 - mean_absolute_error: 0.1515 - val_loss: 9.8314 - val_mean_absolute_error: 2.3307
Epoch 995/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.0597 - mean_absolute_error: 0.1650 - val_loss: 9.5169 - val_mean_absolute_error: 2.3071
Epoch 996/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0607 - mean_absolute_error: 0.1629 - val_loss: 9.3652 - val_mean_absolute_error: 2.2768
Epoch 997/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0533 - mean_absolute_error: 0.1438 - val_loss: 9.5636 - val_mean_absolute_error: 2.3117
Epoch 998/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0644 - mean_absolute_error: 0.1375 - val_loss: 9.7638 - val_mean_absolute_error: 2.3221
Epoch 999/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.0675 - mean_absolute_error: 0.1321 - val_loss: 9.4684 - val_mean_absolute_error: 2.2953
Epoch 1000/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.0612 - mean_absolute_error: 0.1446 - val_loss: 9.6163 - val_mean_absolute_error: 2.3081
7/7 [==============================] - 0s 6ms/step
1/1 [==============================] - 0s 20ms/step
1/1 [==============================] - 0s 22ms/step

# Calculate the RMSE
rmse_lstm = sqrt(mean_squared_error(y_test_BMW, test_predictions_BMW))
print('The RMSE value of LSTM model (BMW): {:.4f}'.format(rmse_lstm))

The RMSE value of LSTM model (BMW): 2.5942

# Plot Training Observations VS Training Predictions 
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_train_BMW, train_predictions_BMW)
plt.plot(dates_train_BMW, y_train_BMW)
plt.title('LSTM: Training Actual Returns/Training Predicted Returns (BMW)', fontsize=16)
plt.legend(['BMW Training Predictions', 'BMW Training Observations'])

# Plot Testing Observations VS Testing Predictions 
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_test_BMW, test_predictions_BMW)
plt.plot(dates_test_BMW, y_test_BMW)
plt.title('LSTM: Testing Actual Returns/Testing Predicted Returns (BMW)', fontsize=16)
plt.legend(['BMW Testing Predictions', 'BMW Testing Observations'])

# General Plot (Training, Validation & testing)
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_train_BMW, train_predictions_BMW)
plt.plot(dates_train_BMW, y_train_BMW)
plt.plot(dates_val_BMW, val_predictions_BMW)
plt.plot(dates_val_BMW, y_val_BMW)
plt.plot(dates_test_BMW, test_predictions_BMW)
plt.plot(dates_test_BMW, y_test_BMW)
plt.title('LSTM: General forecasting plot (BMW)', fontsize=16)
plt.legend(['BMW Training Predictions', 
            'BMW Training Observations',
            'BMW Validation Predictions', 
            'BMW Validation Observations',
            'BMW Testing Predictions', 
            'BMW Testing Observations'])

<matplotlib.legend.Legend at 0x7fa8c31e54f0>

Ford

# transform a time series dataset into a supervised learning dataset (Input : Output)
def F_to_windowed_F(F_RET, first_date_str, last_date_str, n=3):
    first_date = str_to_datetime(first_date_str)
    last_date  = str_to_datetime(last_date_str)
    
    target_date = first_date
    
    dates_F = []
    X, Y = [], []
    
    last_time = False
    while True:
        F_subset = F_RET.loc[:target_date].tail(n+1)
        
        if len(F_subset) != n+1:
            print(f'Error: Window of size {n} is too large for date {target_date}')
            return
        
        values = F_subset['Ret_F'].to_numpy()
        x, y = values[:-1], values[-1]
        
        dates_F.append(target_date)
        X.append(x)
        Y.append(y)
        
        next_week = F_RET.loc[target_date:target_date+datetime.timedelta(days=7)]
        next_datetime_str = str(next_week.head(2).tail(1).index.values[0])
        next_date_str = next_datetime_str.split('T')[0]
        year_month_day = next_date_str.split('-')
        year, month, day = year_month_day
        next_date = datetime.datetime(day=int(day), month=int(month), year=int(year))
        
        if last_time:
            break
        
        target_date = next_date
        
        if target_date == last_date:
            last_time = True
    ret_F = pd.DataFrame({})
    ret_F['Target Date'] = dates_F
    
    X = np.array(X)
    for i in range(0, n):
        X[:, i]
        ret_F[f'Target-{n-i}'] = X[:, i]
        
    ret_F['Target'] = Y
    
    return ret_F

# Start day second time around: '2020-01-03'
windowed_F = F_to_windowed_F(F_RET, 
                                '2020-01-03', 
                                '2020-12-30', 
                                n=3)

# Convert our new dataset into numpy arrays (to feed it directly into a tensorflow model)
def windowed_F_to_date_X_y(windowed_dataframe):
    F_as_np = windowed_dataframe.to_numpy()
    
    dates_F = F_as_np[:, 0] 
    
    middle_matrix_F = F_as_np[:, 1:-1]
    X_F = middle_matrix_F.reshape((len(dates_F), middle_matrix_F.shape[1], 1))
    
    Y_F = F_as_np[:, -1]
    
    return dates_F, X_F.astype(np.float32), Y_F.astype(np.float32)

dates_F, X_F, y_F = windowed_F_to_date_X_y(windowed_F)

# Split the data into training, validation and testing partitions 
q_85_F = int(len(dates_F) * .85)
q_95_F = int(len(dates_F) * .95)

dates_train_F, X_train_F, y_train_F = dates_F[:q_85_F], X_F[:q_85_F], y_F[:q_85_F]
dates_val_F, X_val_F, y_val_F = dates_F[q_85_F:q_95_F], X_F[q_85_F:q_95_F], y_F[q_85_F:q_95_F]
dates_test_F, X_test_F, y_test_F = dates_F[q_95_F:], X_F[q_95_F:], y_F[q_95_F:]

# Create & train the LSTM model 
model_F = Sequential([layers.Input((3, 1)),
                    layers.LSTM(264),
                    layers.Dense(132, activation='relu'),
                    layers.Dense(132, activation='relu'),
                    layers.Dense(1)])

model_F.compile(loss='mse', 
              optimizer=Adam(learning_rate=0.001),
              metrics=['mean_absolute_error'])

# Fitting the LSTM model 
model_F.fit(X_train_F, y_train_F, validation_data=(X_val_F, y_val_F), epochs=1000)

# Forecasting
train_predictions_F = model_F.predict(X_train_F).flatten()
val_predictions_F = model_F.predict(X_val_F).flatten()
test_predictions_F = model_F.predict(X_test_F).flatten()

Epoch 1/1000
7/7 [==============================] - 3s 124ms/step - loss: 14.1291 - mean_absolute_error: 2.5834 - val_loss: 7.0807 - val_mean_absolute_error: 2.0285
Epoch 2/1000
7/7 [==============================] - 0s 26ms/step - loss: 13.9391 - mean_absolute_error: 2.5655 - val_loss: 7.0867 - val_mean_absolute_error: 2.0259
Epoch 3/1000
7/7 [==============================] - 0s 24ms/step - loss: 13.8637 - mean_absolute_error: 2.5562 - val_loss: 7.1496 - val_mean_absolute_error: 2.0390
Epoch 4/1000
7/7 [==============================] - 0s 20ms/step - loss: 13.7357 - mean_absolute_error: 2.5421 - val_loss: 7.3126 - val_mean_absolute_error: 2.0601
Epoch 5/1000
7/7 [==============================] - 0s 27ms/step - loss: 13.5073 - mean_absolute_error: 2.5340 - val_loss: 7.3706 - val_mean_absolute_error: 2.0729
Epoch 6/1000
7/7 [==============================] - 0s 24ms/step - loss: 13.2535 - mean_absolute_error: 2.5173 - val_loss: 7.5392 - val_mean_absolute_error: 2.1168
Epoch 7/1000
7/7 [==============================] - 0s 21ms/step - loss: 13.0932 - mean_absolute_error: 2.5187 - val_loss: 7.8834 - val_mean_absolute_error: 2.1596
Epoch 8/1000
7/7 [==============================] - 0s 21ms/step - loss: 12.8905 - mean_absolute_error: 2.4917 - val_loss: 7.9014 - val_mean_absolute_error: 2.1838
Epoch 9/1000
7/7 [==============================] - 0s 24ms/step - loss: 12.5447 - mean_absolute_error: 2.4584 - val_loss: 8.2498 - val_mean_absolute_error: 2.1904
Epoch 10/1000
7/7 [==============================] - 0s 29ms/step - loss: 12.3602 - mean_absolute_error: 2.4688 - val_loss: 8.5228 - val_mean_absolute_error: 2.2142
Epoch 11/1000
7/7 [==============================] - 0s 21ms/step - loss: 12.0978 - mean_absolute_error: 2.4279 - val_loss: 8.5425 - val_mean_absolute_error: 2.2175
Epoch 12/1000
7/7 [==============================] - 0s 22ms/step - loss: 12.2890 - mean_absolute_error: 2.4367 - val_loss: 8.7267 - val_mean_absolute_error: 2.2576
Epoch 13/1000
7/7 [==============================] - 0s 24ms/step - loss: 12.0918 - mean_absolute_error: 2.4092 - val_loss: 9.0535 - val_mean_absolute_error: 2.3111
Epoch 14/1000
7/7 [==============================] - 0s 22ms/step - loss: 12.0066 - mean_absolute_error: 2.4312 - val_loss: 9.1410 - val_mean_absolute_error: 2.3255
Epoch 15/1000
7/7 [==============================] - 0s 23ms/step - loss: 12.2807 - mean_absolute_error: 2.4416 - val_loss: 8.9239 - val_mean_absolute_error: 2.3264
Epoch 16/1000
7/7 [==============================] - 0s 23ms/step - loss: 11.8921 - mean_absolute_error: 2.4094 - val_loss: 9.4019 - val_mean_absolute_error: 2.3824
Epoch 17/1000
7/7 [==============================] - 0s 23ms/step - loss: 11.7708 - mean_absolute_error: 2.4086 - val_loss: 9.2441 - val_mean_absolute_error: 2.3567
Epoch 18/1000
7/7 [==============================] - 0s 20ms/step - loss: 11.6456 - mean_absolute_error: 2.3842 - val_loss: 9.1971 - val_mean_absolute_error: 2.3654
Epoch 19/1000
7/7 [==============================] - 0s 26ms/step - loss: 11.5662 - mean_absolute_error: 2.3678 - val_loss: 9.2678 - val_mean_absolute_error: 2.3590
Epoch 20/1000
7/7 [==============================] - 0s 25ms/step - loss: 11.4833 - mean_absolute_error: 2.3602 - val_loss: 9.4341 - val_mean_absolute_error: 2.3867
Epoch 21/1000
7/7 [==============================] - 0s 23ms/step - loss: 11.4236 - mean_absolute_error: 2.3533 - val_loss: 10.1684 - val_mean_absolute_error: 2.4899
Epoch 22/1000
7/7 [==============================] - 0s 29ms/step - loss: 11.4527 - mean_absolute_error: 2.3592 - val_loss: 9.9754 - val_mean_absolute_error: 2.4418
Epoch 23/1000
7/7 [==============================] - 0s 22ms/step - loss: 11.2770 - mean_absolute_error: 2.3348 - val_loss: 9.9431 - val_mean_absolute_error: 2.4530
Epoch 24/1000
7/7 [==============================] - 0s 21ms/step - loss: 11.3230 - mean_absolute_error: 2.3392 - val_loss: 9.7826 - val_mean_absolute_error: 2.4282
Epoch 25/1000
7/7 [==============================] - 0s 21ms/step - loss: 11.1675 - mean_absolute_error: 2.3106 - val_loss: 9.4996 - val_mean_absolute_error: 2.3806
Epoch 26/1000
7/7 [==============================] - 0s 23ms/step - loss: 11.1402 - mean_absolute_error: 2.3093 - val_loss: 9.8982 - val_mean_absolute_error: 2.4337
Epoch 27/1000
7/7 [==============================] - 0s 24ms/step - loss: 11.0842 - mean_absolute_error: 2.2957 - val_loss: 10.0753 - val_mean_absolute_error: 2.4645
Epoch 28/1000
7/7 [==============================] - 0s 27ms/step - loss: 11.0275 - mean_absolute_error: 2.2754 - val_loss: 9.9566 - val_mean_absolute_error: 2.4434
Epoch 29/1000
7/7 [==============================] - 0s 27ms/step - loss: 10.9377 - mean_absolute_error: 2.2730 - val_loss: 9.6514 - val_mean_absolute_error: 2.4057
Epoch 30/1000
7/7 [==============================] - 0s 23ms/step - loss: 11.2689 - mean_absolute_error: 2.3121 - val_loss: 9.7499 - val_mean_absolute_error: 2.3991
Epoch 31/1000
7/7 [==============================] - 0s 23ms/step - loss: 10.9052 - mean_absolute_error: 2.2973 - val_loss: 11.2479 - val_mean_absolute_error: 2.5785
Epoch 32/1000
7/7 [==============================] - 0s 25ms/step - loss: 11.1196 - mean_absolute_error: 2.3347 - val_loss: 10.4624 - val_mean_absolute_error: 2.5108
Epoch 33/1000
7/7 [==============================] - 0s 23ms/step - loss: 10.9622 - mean_absolute_error: 2.2944 - val_loss: 9.9672 - val_mean_absolute_error: 2.4432
Epoch 34/1000
7/7 [==============================] - 0s 29ms/step - loss: 10.8660 - mean_absolute_error: 2.2960 - val_loss: 9.8879 - val_mean_absolute_error: 2.3868
Epoch 35/1000
7/7 [==============================] - 0s 25ms/step - loss: 10.8594 - mean_absolute_error: 2.3280 - val_loss: 9.8612 - val_mean_absolute_error: 2.3811
Epoch 36/1000
7/7 [==============================] - 0s 38ms/step - loss: 10.3712 - mean_absolute_error: 2.2288 - val_loss: 9.5292 - val_mean_absolute_error: 2.3426
Epoch 37/1000
7/7 [==============================] - 0s 21ms/step - loss: 10.4636 - mean_absolute_error: 2.2212 - val_loss: 9.8332 - val_mean_absolute_error: 2.4108
Epoch 38/1000
7/7 [==============================] - 0s 19ms/step - loss: 10.2697 - mean_absolute_error: 2.2034 - val_loss: 10.2315 - val_mean_absolute_error: 2.4906
Epoch 39/1000
7/7 [==============================] - 0s 20ms/step - loss: 10.1839 - mean_absolute_error: 2.1847 - val_loss: 10.4087 - val_mean_absolute_error: 2.4769
Epoch 40/1000
7/7 [==============================] - 0s 19ms/step - loss: 10.0477 - mean_absolute_error: 2.1751 - val_loss: 9.6564 - val_mean_absolute_error: 2.3301
Epoch 41/1000
7/7 [==============================] - 0s 22ms/step - loss: 10.0771 - mean_absolute_error: 2.1842 - val_loss: 9.2985 - val_mean_absolute_error: 2.3024
Epoch 42/1000
7/7 [==============================] - 0s 20ms/step - loss: 9.8644 - mean_absolute_error: 2.1624 - val_loss: 9.7696 - val_mean_absolute_error: 2.3851
Epoch 43/1000
7/7 [==============================] - 0s 23ms/step - loss: 9.8827 - mean_absolute_error: 2.1357 - val_loss: 10.2205 - val_mean_absolute_error: 2.4393
Epoch 44/1000
7/7 [==============================] - 0s 23ms/step - loss: 9.7565 - mean_absolute_error: 2.1430 - val_loss: 10.5909 - val_mean_absolute_error: 2.4802
Epoch 45/1000
7/7 [==============================] - 0s 21ms/step - loss: 9.5599 - mean_absolute_error: 2.1212 - val_loss: 10.0780 - val_mean_absolute_error: 2.4159
Epoch 46/1000
7/7 [==============================] - 0s 21ms/step - loss: 9.4101 - mean_absolute_error: 2.0912 - val_loss: 9.8604 - val_mean_absolute_error: 2.3731
Epoch 47/1000
7/7 [==============================] - 0s 19ms/step - loss: 9.3061 - mean_absolute_error: 2.0897 - val_loss: 9.6991 - val_mean_absolute_error: 2.3411
Epoch 48/1000
7/7 [==============================] - 0s 21ms/step - loss: 9.1731 - mean_absolute_error: 2.0701 - val_loss: 9.9547 - val_mean_absolute_error: 2.3612
Epoch 49/1000
7/7 [==============================] - 0s 25ms/step - loss: 9.6322 - mean_absolute_error: 2.1471 - val_loss: 9.4072 - val_mean_absolute_error: 2.2369
Epoch 50/1000
7/7 [==============================] - 0s 21ms/step - loss: 9.4552 - mean_absolute_error: 2.1394 - val_loss: 9.8122 - val_mean_absolute_error: 2.3697
Epoch 51/1000
7/7 [==============================] - 0s 20ms/step - loss: 9.4339 - mean_absolute_error: 2.1118 - val_loss: 9.1650 - val_mean_absolute_error: 2.2030
Epoch 52/1000
7/7 [==============================] - 0s 19ms/step - loss: 9.0728 - mean_absolute_error: 2.1237 - val_loss: 10.5546 - val_mean_absolute_error: 2.3795
Epoch 53/1000
7/7 [==============================] - 0s 21ms/step - loss: 9.6263 - mean_absolute_error: 2.1508 - val_loss: 11.5147 - val_mean_absolute_error: 2.5186
Epoch 54/1000
7/7 [==============================] - 0s 22ms/step - loss: 8.7771 - mean_absolute_error: 2.0550 - val_loss: 9.4583 - val_mean_absolute_error: 2.2238
Epoch 55/1000
7/7 [==============================] - 0s 22ms/step - loss: 8.9534 - mean_absolute_error: 2.1004 - val_loss: 10.0321 - val_mean_absolute_error: 2.3026
Epoch 56/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.5854 - mean_absolute_error: 2.0314 - val_loss: 11.1471 - val_mean_absolute_error: 2.4122
Epoch 57/1000
7/7 [==============================] - 0s 18ms/step - loss: 8.3890 - mean_absolute_error: 2.0036 - val_loss: 11.4214 - val_mean_absolute_error: 2.4737
Epoch 58/1000
7/7 [==============================] - 0s 21ms/step - loss: 8.2104 - mean_absolute_error: 2.0119 - val_loss: 10.7860 - val_mean_absolute_error: 2.4429
Epoch 59/1000
7/7 [==============================] - 0s 21ms/step - loss: 8.6702 - mean_absolute_error: 2.0398 - val_loss: 10.1954 - val_mean_absolute_error: 2.3537
Epoch 60/1000
7/7 [==============================] - 0s 21ms/step - loss: 8.3662 - mean_absolute_error: 2.0314 - val_loss: 10.6478 - val_mean_absolute_error: 2.3401
Epoch 61/1000
7/7 [==============================] - 0s 19ms/step - loss: 8.1682 - mean_absolute_error: 2.0293 - val_loss: 11.3555 - val_mean_absolute_error: 2.4043
Epoch 62/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.7714 - mean_absolute_error: 1.9552 - val_loss: 12.3390 - val_mean_absolute_error: 2.6163
Epoch 63/1000
7/7 [==============================] - 0s 29ms/step - loss: 7.6841 - mean_absolute_error: 1.9462 - val_loss: 11.5072 - val_mean_absolute_error: 2.5035
Epoch 64/1000
7/7 [==============================] - 0s 20ms/step - loss: 7.4644 - mean_absolute_error: 1.9046 - val_loss: 12.8641 - val_mean_absolute_error: 2.6359
Epoch 65/1000
7/7 [==============================] - 0s 20ms/step - loss: 7.4082 - mean_absolute_error: 1.9244 - val_loss: 12.0557 - val_mean_absolute_error: 2.5560
Epoch 66/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.2827 - mean_absolute_error: 1.8911 - val_loss: 11.7973 - val_mean_absolute_error: 2.4734
Epoch 67/1000
7/7 [==============================] - 0s 18ms/step - loss: 7.0079 - mean_absolute_error: 1.8802 - val_loss: 11.9206 - val_mean_absolute_error: 2.4847
Epoch 68/1000
7/7 [==============================] - 0s 19ms/step - loss: 7.0091 - mean_absolute_error: 1.8499 - val_loss: 13.1290 - val_mean_absolute_error: 2.6753
Epoch 69/1000
7/7 [==============================] - 0s 18ms/step - loss: 6.8455 - mean_absolute_error: 1.8620 - val_loss: 12.4971 - val_mean_absolute_error: 2.5650
Epoch 70/1000
7/7 [==============================] - 0s 29ms/step - loss: 6.6914 - mean_absolute_error: 1.8285 - val_loss: 12.4712 - val_mean_absolute_error: 2.6004
Epoch 71/1000
7/7 [==============================] - 0s 22ms/step - loss: 6.9221 - mean_absolute_error: 1.8876 - val_loss: 12.9546 - val_mean_absolute_error: 2.5729
Epoch 72/1000
7/7 [==============================] - 0s 25ms/step - loss: 7.0243 - mean_absolute_error: 1.9262 - val_loss: 13.4260 - val_mean_absolute_error: 2.6940
Epoch 73/1000
7/7 [==============================] - 0s 20ms/step - loss: 7.5388 - mean_absolute_error: 1.9851 - val_loss: 12.5164 - val_mean_absolute_error: 2.5778
Epoch 74/1000
7/7 [==============================] - 0s 21ms/step - loss: 6.6167 - mean_absolute_error: 1.8804 - val_loss: 11.6695 - val_mean_absolute_error: 2.4646
Epoch 75/1000
7/7 [==============================] - 0s 24ms/step - loss: 6.4589 - mean_absolute_error: 1.8717 - val_loss: 13.0322 - val_mean_absolute_error: 2.6288
Epoch 76/1000
7/7 [==============================] - 0s 20ms/step - loss: 6.4966 - mean_absolute_error: 1.8898 - val_loss: 12.5415 - val_mean_absolute_error: 2.5807
Epoch 77/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.3987 - mean_absolute_error: 1.8664 - val_loss: 13.0951 - val_mean_absolute_error: 2.6581
Epoch 78/1000
7/7 [==============================] - 0s 19ms/step - loss: 6.7639 - mean_absolute_error: 1.8968 - val_loss: 12.9709 - val_mean_absolute_error: 2.6692
Epoch 79/1000
7/7 [==============================] - 0s 20ms/step - loss: 5.9949 - mean_absolute_error: 1.8029 - val_loss: 12.0733 - val_mean_absolute_error: 2.5223
Epoch 80/1000
7/7 [==============================] - 0s 20ms/step - loss: 6.3129 - mean_absolute_error: 1.8373 - val_loss: 13.8091 - val_mean_absolute_error: 2.7022
Epoch 81/1000
7/7 [==============================] - 0s 18ms/step - loss: 5.9129 - mean_absolute_error: 1.8043 - val_loss: 12.6100 - val_mean_absolute_error: 2.6540
Epoch 82/1000
7/7 [==============================] - 0s 21ms/step - loss: 5.6354 - mean_absolute_error: 1.7401 - val_loss: 14.1394 - val_mean_absolute_error: 2.8373
Epoch 83/1000
7/7 [==============================] - 0s 22ms/step - loss: 5.7268 - mean_absolute_error: 1.7499 - val_loss: 12.1423 - val_mean_absolute_error: 2.4822
Epoch 84/1000
7/7 [==============================] - 0s 22ms/step - loss: 5.5299 - mean_absolute_error: 1.7314 - val_loss: 12.9598 - val_mean_absolute_error: 2.6353
Epoch 85/1000
7/7 [==============================] - 0s 30ms/step - loss: 5.2637 - mean_absolute_error: 1.7017 - val_loss: 13.3887 - val_mean_absolute_error: 2.6412
Epoch 86/1000
7/7 [==============================] - 0s 36ms/step - loss: 5.3491 - mean_absolute_error: 1.7002 - val_loss: 12.8123 - val_mean_absolute_error: 2.5599
Epoch 87/1000
7/7 [==============================] - 0s 21ms/step - loss: 5.1733 - mean_absolute_error: 1.6542 - val_loss: 13.6525 - val_mean_absolute_error: 2.7312
Epoch 88/1000
7/7 [==============================] - 0s 21ms/step - loss: 4.9805 - mean_absolute_error: 1.6382 - val_loss: 12.8467 - val_mean_absolute_error: 2.5891
Epoch 89/1000
7/7 [==============================] - 0s 22ms/step - loss: 5.0993 - mean_absolute_error: 1.6193 - val_loss: 12.6817 - val_mean_absolute_error: 2.5892
Epoch 90/1000
7/7 [==============================] - 0s 21ms/step - loss: 4.8983 - mean_absolute_error: 1.6560 - val_loss: 12.7878 - val_mean_absolute_error: 2.6190
Epoch 91/1000
7/7 [==============================] - 0s 22ms/step - loss: 5.4589 - mean_absolute_error: 1.7004 - val_loss: 13.1430 - val_mean_absolute_error: 2.6419
Epoch 92/1000
7/7 [==============================] - 0s 26ms/step - loss: 5.0386 - mean_absolute_error: 1.6907 - val_loss: 11.3990 - val_mean_absolute_error: 2.4243
Epoch 93/1000
7/7 [==============================] - 0s 26ms/step - loss: 5.0478 - mean_absolute_error: 1.6749 - val_loss: 13.6774 - val_mean_absolute_error: 2.7554
Epoch 94/1000
7/7 [==============================] - 0s 24ms/step - loss: 4.9821 - mean_absolute_error: 1.6601 - val_loss: 12.8103 - val_mean_absolute_error: 2.6776
Epoch 95/1000
7/7 [==============================] - 0s 22ms/step - loss: 4.7534 - mean_absolute_error: 1.6283 - val_loss: 11.9806 - val_mean_absolute_error: 2.5470
Epoch 96/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.9204 - mean_absolute_error: 1.6358 - val_loss: 12.0236 - val_mean_absolute_error: 2.4582
Epoch 97/1000
7/7 [==============================] - 0s 19ms/step - loss: 5.0187 - mean_absolute_error: 1.6001 - val_loss: 13.1244 - val_mean_absolute_error: 2.7101
Epoch 98/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.8168 - mean_absolute_error: 1.6541 - val_loss: 12.2610 - val_mean_absolute_error: 2.5396
Epoch 99/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.8922 - mean_absolute_error: 1.6271 - val_loss: 12.1913 - val_mean_absolute_error: 2.5053
Epoch 100/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.4846 - mean_absolute_error: 1.5753 - val_loss: 12.7141 - val_mean_absolute_error: 2.5651
Epoch 101/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.4748 - mean_absolute_error: 1.5224 - val_loss: 12.9386 - val_mean_absolute_error: 2.5972
Epoch 102/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.3134 - mean_absolute_error: 1.5033 - val_loss: 12.2761 - val_mean_absolute_error: 2.5157
Epoch 103/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.5615 - mean_absolute_error: 1.5840 - val_loss: 12.5085 - val_mean_absolute_error: 2.6141
Epoch 104/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.4717 - mean_absolute_error: 1.5910 - val_loss: 12.7984 - val_mean_absolute_error: 2.5784
Epoch 105/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.7943 - mean_absolute_error: 1.6286 - val_loss: 12.9117 - val_mean_absolute_error: 2.5846
Epoch 106/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.4746 - mean_absolute_error: 1.5722 - val_loss: 11.9590 - val_mean_absolute_error: 2.5496
Epoch 107/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.3978 - mean_absolute_error: 1.5629 - val_loss: 12.5658 - val_mean_absolute_error: 2.5899
Epoch 108/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.5448 - mean_absolute_error: 1.5561 - val_loss: 12.5212 - val_mean_absolute_error: 2.5496
Epoch 109/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.7927 - mean_absolute_error: 1.6331 - val_loss: 11.6538 - val_mean_absolute_error: 2.4354
Epoch 110/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.4088 - mean_absolute_error: 1.5389 - val_loss: 13.2356 - val_mean_absolute_error: 2.6646
Epoch 111/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.2269 - mean_absolute_error: 1.4840 - val_loss: 12.8991 - val_mean_absolute_error: 2.6198
Epoch 112/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.2605 - mean_absolute_error: 1.4988 - val_loss: 12.9676 - val_mean_absolute_error: 2.6025
Epoch 113/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.1807 - mean_absolute_error: 1.4784 - val_loss: 12.1279 - val_mean_absolute_error: 2.5262
Epoch 114/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.0636 - mean_absolute_error: 1.4303 - val_loss: 12.3803 - val_mean_absolute_error: 2.6003
Epoch 115/1000
7/7 [==============================] - 0s 18ms/step - loss: 4.0812 - mean_absolute_error: 1.4412 - val_loss: 12.7715 - val_mean_absolute_error: 2.6361
Epoch 116/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.0374 - mean_absolute_error: 1.4427 - val_loss: 12.8340 - val_mean_absolute_error: 2.6313
Epoch 117/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.0925 - mean_absolute_error: 1.4380 - val_loss: 13.3917 - val_mean_absolute_error: 2.6874
Epoch 118/1000
7/7 [==============================] - 0s 20ms/step - loss: 4.5724 - mean_absolute_error: 1.5534 - val_loss: 13.0678 - val_mean_absolute_error: 2.7240
Epoch 119/1000
7/7 [==============================] - 0s 23ms/step - loss: 5.3190 - mean_absolute_error: 1.6742 - val_loss: 10.8514 - val_mean_absolute_error: 2.4352
Epoch 120/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.7900 - mean_absolute_error: 1.6292 - val_loss: 10.7903 - val_mean_absolute_error: 2.3793
Epoch 121/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.3578 - mean_absolute_error: 1.5544 - val_loss: 12.8346 - val_mean_absolute_error: 2.6465
Epoch 122/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.1827 - mean_absolute_error: 1.4880 - val_loss: 11.9892 - val_mean_absolute_error: 2.5906
Epoch 123/1000
7/7 [==============================] - 0s 19ms/step - loss: 4.0604 - mean_absolute_error: 1.4487 - val_loss: 11.8953 - val_mean_absolute_error: 2.5018
Epoch 124/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.9625 - mean_absolute_error: 1.4475 - val_loss: 12.4267 - val_mean_absolute_error: 2.5983
Epoch 125/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.9370 - mean_absolute_error: 1.4467 - val_loss: 12.3596 - val_mean_absolute_error: 2.6043
Epoch 126/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.9902 - mean_absolute_error: 1.4342 - val_loss: 13.3795 - val_mean_absolute_error: 2.7398
Epoch 127/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.8220 - mean_absolute_error: 1.3993 - val_loss: 12.0435 - val_mean_absolute_error: 2.5931
Epoch 128/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.8076 - mean_absolute_error: 1.3764 - val_loss: 12.6425 - val_mean_absolute_error: 2.6172
Epoch 129/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.9072 - mean_absolute_error: 1.4311 - val_loss: 12.7946 - val_mean_absolute_error: 2.6661
Epoch 130/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.6822 - mean_absolute_error: 1.3425 - val_loss: 12.9398 - val_mean_absolute_error: 2.6344
Epoch 131/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.5976 - mean_absolute_error: 1.3208 - val_loss: 13.3665 - val_mean_absolute_error: 2.7415
Epoch 132/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.6254 - mean_absolute_error: 1.3508 - val_loss: 12.8389 - val_mean_absolute_error: 2.6432
Epoch 133/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.7661 - mean_absolute_error: 1.3654 - val_loss: 12.5308 - val_mean_absolute_error: 2.5510
Epoch 134/1000
7/7 [==============================] - 0s 32ms/step - loss: 3.7588 - mean_absolute_error: 1.4257 - val_loss: 12.1947 - val_mean_absolute_error: 2.5241
Epoch 135/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.7844 - mean_absolute_error: 1.4215 - val_loss: 13.2723 - val_mean_absolute_error: 2.6925
Epoch 136/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.7948 - mean_absolute_error: 1.4030 - val_loss: 12.9800 - val_mean_absolute_error: 2.6816
Epoch 137/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.7212 - mean_absolute_error: 1.3742 - val_loss: 12.1198 - val_mean_absolute_error: 2.6034
Epoch 138/1000
7/7 [==============================] - 0s 31ms/step - loss: 3.5539 - mean_absolute_error: 1.3352 - val_loss: 13.6189 - val_mean_absolute_error: 2.7744
Epoch 139/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.4228 - mean_absolute_error: 1.3061 - val_loss: 11.9345 - val_mean_absolute_error: 2.5933
Epoch 140/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.4839 - mean_absolute_error: 1.3042 - val_loss: 12.4128 - val_mean_absolute_error: 2.5863
Epoch 141/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.3998 - mean_absolute_error: 1.3211 - val_loss: 12.9665 - val_mean_absolute_error: 2.6662
Epoch 142/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.3544 - mean_absolute_error: 1.3186 - val_loss: 13.4429 - val_mean_absolute_error: 2.7686
Epoch 143/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.2953 - mean_absolute_error: 1.2975 - val_loss: 12.5163 - val_mean_absolute_error: 2.5821
Epoch 144/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.5624 - mean_absolute_error: 1.3875 - val_loss: 13.1517 - val_mean_absolute_error: 2.7119
Epoch 145/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.4252 - mean_absolute_error: 1.3155 - val_loss: 13.5772 - val_mean_absolute_error: 2.7827
Epoch 146/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.3175 - mean_absolute_error: 1.3082 - val_loss: 11.6494 - val_mean_absolute_error: 2.4498
Epoch 147/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.6939 - mean_absolute_error: 1.4229 - val_loss: 13.5035 - val_mean_absolute_error: 2.8318
Epoch 148/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.2595 - mean_absolute_error: 1.3223 - val_loss: 12.9898 - val_mean_absolute_error: 2.6285
Epoch 149/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.3602 - mean_absolute_error: 1.3630 - val_loss: 12.3865 - val_mean_absolute_error: 2.6420
Epoch 150/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.3373 - mean_absolute_error: 1.3661 - val_loss: 13.0974 - val_mean_absolute_error: 2.6474
Epoch 151/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.6068 - mean_absolute_error: 1.4040 - val_loss: 13.1605 - val_mean_absolute_error: 2.8049
Epoch 152/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.6816 - mean_absolute_error: 1.3840 - val_loss: 12.2167 - val_mean_absolute_error: 2.5752
Epoch 153/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.4484 - mean_absolute_error: 1.2914 - val_loss: 12.8059 - val_mean_absolute_error: 2.6432
Epoch 154/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.6312 - mean_absolute_error: 1.3836 - val_loss: 11.0081 - val_mean_absolute_error: 2.4339
Epoch 155/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.4939 - mean_absolute_error: 1.3642 - val_loss: 14.0373 - val_mean_absolute_error: 2.8023
Epoch 156/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.2330 - mean_absolute_error: 1.2975 - val_loss: 12.0166 - val_mean_absolute_error: 2.5226
Epoch 157/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.2356 - mean_absolute_error: 1.3089 - val_loss: 11.7925 - val_mean_absolute_error: 2.6520
Epoch 158/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.7263 - mean_absolute_error: 1.4211 - val_loss: 11.8615 - val_mean_absolute_error: 2.6078
Epoch 159/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.5285 - mean_absolute_error: 1.3405 - val_loss: 11.1144 - val_mean_absolute_error: 2.5904
Epoch 160/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.4357 - mean_absolute_error: 1.3388 - val_loss: 13.3690 - val_mean_absolute_error: 2.7391
Epoch 161/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.2339 - mean_absolute_error: 1.3087 - val_loss: 12.3865 - val_mean_absolute_error: 2.6297
Epoch 162/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.2275 - mean_absolute_error: 1.2518 - val_loss: 12.5710 - val_mean_absolute_error: 2.6783
Epoch 163/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.9112 - mean_absolute_error: 1.2018 - val_loss: 12.8073 - val_mean_absolute_error: 2.6621
Epoch 164/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.8290 - mean_absolute_error: 1.1839 - val_loss: 12.1106 - val_mean_absolute_error: 2.6450
Epoch 165/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.9259 - mean_absolute_error: 1.1866 - val_loss: 12.4660 - val_mean_absolute_error: 2.6539
Epoch 166/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.6875 - mean_absolute_error: 1.1252 - val_loss: 12.6145 - val_mean_absolute_error: 2.7030
Epoch 167/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.5966 - mean_absolute_error: 1.1212 - val_loss: 12.6631 - val_mean_absolute_error: 2.6601
Epoch 168/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.8397 - mean_absolute_error: 1.2279 - val_loss: 12.5011 - val_mean_absolute_error: 2.7734
Epoch 169/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.2086 - mean_absolute_error: 1.2937 - val_loss: 12.3550 - val_mean_absolute_error: 2.5688
Epoch 170/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.0148 - mean_absolute_error: 1.2469 - val_loss: 14.2958 - val_mean_absolute_error: 2.8973
Epoch 171/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.8080 - mean_absolute_error: 1.2321 - val_loss: 11.6233 - val_mean_absolute_error: 2.4659
Epoch 172/1000
7/7 [==============================] - 0s 22ms/step - loss: 2.9393 - mean_absolute_error: 1.2530 - val_loss: 12.5321 - val_mean_absolute_error: 2.7078
Epoch 173/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.0991 - mean_absolute_error: 1.2047 - val_loss: 12.5364 - val_mean_absolute_error: 2.7058
Epoch 174/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.8899 - mean_absolute_error: 1.2079 - val_loss: 11.8117 - val_mean_absolute_error: 2.5581
Epoch 175/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.8351 - mean_absolute_error: 1.1899 - val_loss: 12.9878 - val_mean_absolute_error: 2.7698
Epoch 176/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.9249 - mean_absolute_error: 1.1854 - val_loss: 12.2197 - val_mean_absolute_error: 2.6325
Epoch 177/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.5959 - mean_absolute_error: 1.3331 - val_loss: 11.0748 - val_mean_absolute_error: 2.5442
Epoch 178/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.2349 - mean_absolute_error: 1.3051 - val_loss: 13.5277 - val_mean_absolute_error: 2.7539
Epoch 179/1000
7/7 [==============================] - 0s 18ms/step - loss: 3.3604 - mean_absolute_error: 1.3233 - val_loss: 14.6791 - val_mean_absolute_error: 2.8941
Epoch 180/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.1522 - mean_absolute_error: 1.2955 - val_loss: 12.1551 - val_mean_absolute_error: 2.6451
Epoch 181/1000
7/7 [==============================] - 0s 20ms/step - loss: 3.1939 - mean_absolute_error: 1.3001 - val_loss: 13.2004 - val_mean_absolute_error: 2.8204
Epoch 182/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.7504 - mean_absolute_error: 1.1616 - val_loss: 12.1828 - val_mean_absolute_error: 2.6402
Epoch 183/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.0820 - mean_absolute_error: 1.1765 - val_loss: 13.2203 - val_mean_absolute_error: 2.7731
Epoch 184/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.7338 - mean_absolute_error: 1.1463 - val_loss: 12.4024 - val_mean_absolute_error: 2.6232
Epoch 185/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.9204 - mean_absolute_error: 1.1880 - val_loss: 12.0039 - val_mean_absolute_error: 2.5965
Epoch 186/1000
7/7 [==============================] - 0s 19ms/step - loss: 3.0240 - mean_absolute_error: 1.1721 - val_loss: 13.5304 - val_mean_absolute_error: 2.8214
Epoch 187/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.7981 - mean_absolute_error: 1.1683 - val_loss: 11.4403 - val_mean_absolute_error: 2.5787
Epoch 188/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.8102 - mean_absolute_error: 1.1634 - val_loss: 13.3523 - val_mean_absolute_error: 2.7992
Epoch 189/1000
7/7 [==============================] - 0s 29ms/step - loss: 2.5213 - mean_absolute_error: 1.0929 - val_loss: 12.5005 - val_mean_absolute_error: 2.7203
Epoch 190/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5505 - mean_absolute_error: 1.0848 - val_loss: 12.4204 - val_mean_absolute_error: 2.7069
Epoch 191/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5942 - mean_absolute_error: 1.0935 - val_loss: 13.1597 - val_mean_absolute_error: 2.7577
Epoch 192/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5254 - mean_absolute_error: 1.0903 - val_loss: 12.2041 - val_mean_absolute_error: 2.6652
Epoch 193/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.4851 - mean_absolute_error: 1.0758 - val_loss: 12.6433 - val_mean_absolute_error: 2.7398
Epoch 194/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4414 - mean_absolute_error: 1.0455 - val_loss: 12.6697 - val_mean_absolute_error: 2.7087
Epoch 195/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5706 - mean_absolute_error: 1.0616 - val_loss: 13.2566 - val_mean_absolute_error: 2.7952
Epoch 196/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.5779 - mean_absolute_error: 1.1351 - val_loss: 11.7363 - val_mean_absolute_error: 2.6235
Epoch 197/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.9422 - mean_absolute_error: 1.1798 - val_loss: 12.2922 - val_mean_absolute_error: 2.6092
Epoch 198/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.7394 - mean_absolute_error: 1.1256 - val_loss: 13.2882 - val_mean_absolute_error: 2.8366
Epoch 199/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.4540 - mean_absolute_error: 1.0731 - val_loss: 11.7355 - val_mean_absolute_error: 2.6240
Epoch 200/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.3097 - mean_absolute_error: 0.9956 - val_loss: 12.9903 - val_mean_absolute_error: 2.7603
Epoch 201/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.2802 - mean_absolute_error: 0.9937 - val_loss: 11.9330 - val_mean_absolute_error: 2.6054
Epoch 202/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.2249 - mean_absolute_error: 0.9767 - val_loss: 13.6016 - val_mean_absolute_error: 2.8245
Epoch 203/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.3221 - mean_absolute_error: 1.0519 - val_loss: 12.3704 - val_mean_absolute_error: 2.6876
Epoch 204/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4337 - mean_absolute_error: 1.0849 - val_loss: 13.3206 - val_mean_absolute_error: 2.8483
Epoch 205/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.3430 - mean_absolute_error: 1.0738 - val_loss: 11.8012 - val_mean_absolute_error: 2.6121
Epoch 206/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.2496 - mean_absolute_error: 1.0179 - val_loss: 12.6676 - val_mean_absolute_error: 2.7548
Epoch 207/1000
7/7 [==============================] - 0s 29ms/step - loss: 2.1550 - mean_absolute_error: 0.9799 - val_loss: 12.4762 - val_mean_absolute_error: 2.7025
Epoch 208/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.0954 - mean_absolute_error: 0.9359 - val_loss: 12.6444 - val_mean_absolute_error: 2.6873
Epoch 209/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.0372 - mean_absolute_error: 0.9131 - val_loss: 12.6689 - val_mean_absolute_error: 2.7301
Epoch 210/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.0144 - mean_absolute_error: 0.8845 - val_loss: 12.7219 - val_mean_absolute_error: 2.7553
Epoch 211/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.8752 - mean_absolute_error: 0.8527 - val_loss: 12.5695 - val_mean_absolute_error: 2.7437
Epoch 212/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.0249 - mean_absolute_error: 0.9187 - val_loss: 13.0968 - val_mean_absolute_error: 2.7925
Epoch 213/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8433 - mean_absolute_error: 0.8664 - val_loss: 12.4806 - val_mean_absolute_error: 2.7352
Epoch 214/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.0824 - mean_absolute_error: 0.9203 - val_loss: 12.5848 - val_mean_absolute_error: 2.7478
Epoch 215/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.1226 - mean_absolute_error: 0.9491 - val_loss: 13.0096 - val_mean_absolute_error: 2.7732
Epoch 216/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.0126 - mean_absolute_error: 0.8887 - val_loss: 13.1353 - val_mean_absolute_error: 2.7888
Epoch 217/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9563 - mean_absolute_error: 0.8919 - val_loss: 12.8032 - val_mean_absolute_error: 2.8377
Epoch 218/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.0272 - mean_absolute_error: 0.9038 - val_loss: 13.9299 - val_mean_absolute_error: 2.9011
Epoch 219/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8432 - mean_absolute_error: 0.8343 - val_loss: 12.9312 - val_mean_absolute_error: 2.8020
Epoch 220/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.8907 - mean_absolute_error: 0.8689 - val_loss: 12.2918 - val_mean_absolute_error: 2.7197
Epoch 221/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.8501 - mean_absolute_error: 0.8429 - val_loss: 12.9125 - val_mean_absolute_error: 2.7686
Epoch 222/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.9082 - mean_absolute_error: 0.8791 - val_loss: 13.3334 - val_mean_absolute_error: 2.8561
Epoch 223/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.9930 - mean_absolute_error: 0.9110 - val_loss: 12.6594 - val_mean_absolute_error: 2.8168
Epoch 224/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.8216 - mean_absolute_error: 0.8646 - val_loss: 12.8373 - val_mean_absolute_error: 2.7311
Epoch 225/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.7863 - mean_absolute_error: 0.8227 - val_loss: 12.7251 - val_mean_absolute_error: 2.8176
Epoch 226/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.7250 - mean_absolute_error: 0.8228 - val_loss: 12.6748 - val_mean_absolute_error: 2.7820
Epoch 227/1000
7/7 [==============================] - 0s 25ms/step - loss: 1.6162 - mean_absolute_error: 0.7703 - val_loss: 12.5986 - val_mean_absolute_error: 2.7811
Epoch 228/1000
7/7 [==============================] - 0s 28ms/step - loss: 1.7073 - mean_absolute_error: 0.7871 - val_loss: 13.0593 - val_mean_absolute_error: 2.7875
Epoch 229/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.6276 - mean_absolute_error: 0.7658 - val_loss: 12.3247 - val_mean_absolute_error: 2.7630
Epoch 230/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.6606 - mean_absolute_error: 0.7907 - val_loss: 12.9973 - val_mean_absolute_error: 2.8289
Epoch 231/1000
7/7 [==============================] - 0s 25ms/step - loss: 1.6364 - mean_absolute_error: 0.7740 - val_loss: 12.8169 - val_mean_absolute_error: 2.7883
Epoch 232/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.6634 - mean_absolute_error: 0.8055 - val_loss: 11.8988 - val_mean_absolute_error: 2.6359
Epoch 233/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.8246 - mean_absolute_error: 0.8452 - val_loss: 12.9469 - val_mean_absolute_error: 2.8024
Epoch 234/1000
7/7 [==============================] - 0s 24ms/step - loss: 1.7502 - mean_absolute_error: 0.8380 - val_loss: 12.9357 - val_mean_absolute_error: 2.7950
Epoch 235/1000
7/7 [==============================] - 0s 22ms/step - loss: 2.0699 - mean_absolute_error: 0.9305 - val_loss: 12.1917 - val_mean_absolute_error: 2.7349
Epoch 236/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9253 - mean_absolute_error: 0.8379 - val_loss: 13.6970 - val_mean_absolute_error: 2.8810
Epoch 237/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.7554 - mean_absolute_error: 0.7932 - val_loss: 13.4254 - val_mean_absolute_error: 2.8723
Epoch 238/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.6954 - mean_absolute_error: 0.7541 - val_loss: 12.6958 - val_mean_absolute_error: 2.7500
Epoch 239/1000
7/7 [==============================] - 0s 29ms/step - loss: 1.7547 - mean_absolute_error: 0.7648 - val_loss: 12.9633 - val_mean_absolute_error: 2.7602
Epoch 240/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.7530 - mean_absolute_error: 0.7943 - val_loss: 13.1979 - val_mean_absolute_error: 2.8781
Epoch 241/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.7037 - mean_absolute_error: 0.7861 - val_loss: 13.1071 - val_mean_absolute_error: 2.8029
Epoch 242/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.9248 - mean_absolute_error: 0.8296 - val_loss: 13.0066 - val_mean_absolute_error: 2.8164
Epoch 243/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.5882 - mean_absolute_error: 0.7459 - val_loss: 12.6333 - val_mean_absolute_error: 2.7319
Epoch 244/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8606 - mean_absolute_error: 0.8263 - val_loss: 13.0265 - val_mean_absolute_error: 2.8511
Epoch 245/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.8530 - mean_absolute_error: 0.8601 - val_loss: 13.3213 - val_mean_absolute_error: 2.8676
Epoch 246/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.7456 - mean_absolute_error: 0.7971 - val_loss: 13.4899 - val_mean_absolute_error: 2.8914
Epoch 247/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.6925 - mean_absolute_error: 0.7906 - val_loss: 13.3816 - val_mean_absolute_error: 2.8236
Epoch 248/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5968 - mean_absolute_error: 0.7499 - val_loss: 12.8973 - val_mean_absolute_error: 2.7539
Epoch 249/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.5786 - mean_absolute_error: 0.7472 - val_loss: 14.1887 - val_mean_absolute_error: 2.9147
Epoch 250/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5852 - mean_absolute_error: 0.7595 - val_loss: 12.6440 - val_mean_absolute_error: 2.7761
Epoch 251/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.7665 - mean_absolute_error: 0.7582 - val_loss: 15.3928 - val_mean_absolute_error: 3.0514
Epoch 252/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.6436 - mean_absolute_error: 1.0523 - val_loss: 11.2492 - val_mean_absolute_error: 2.2380
Epoch 253/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4847 - mean_absolute_error: 1.0604 - val_loss: 16.6632 - val_mean_absolute_error: 3.1085
Epoch 254/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4676 - mean_absolute_error: 1.0815 - val_loss: 12.8716 - val_mean_absolute_error: 2.5552
Epoch 255/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4281 - mean_absolute_error: 1.0794 - val_loss: 14.3597 - val_mean_absolute_error: 2.9785
Epoch 256/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.3006 - mean_absolute_error: 1.0966 - val_loss: 12.3875 - val_mean_absolute_error: 2.7427
Epoch 257/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.9518 - mean_absolute_error: 0.9106 - val_loss: 13.8281 - val_mean_absolute_error: 2.9135
Epoch 258/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.9384 - mean_absolute_error: 0.9405 - val_loss: 13.3481 - val_mean_absolute_error: 2.8067
Epoch 259/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.7486 - mean_absolute_error: 0.8737 - val_loss: 12.6535 - val_mean_absolute_error: 2.7880
Epoch 260/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.7311 - mean_absolute_error: 0.8479 - val_loss: 12.7116 - val_mean_absolute_error: 2.7596
Epoch 261/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.5309 - mean_absolute_error: 0.8201 - val_loss: 13.3832 - val_mean_absolute_error: 2.7163
Epoch 262/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.4727 - mean_absolute_error: 0.8042 - val_loss: 13.7870 - val_mean_absolute_error: 2.8969
Epoch 263/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.5041 - mean_absolute_error: 0.8090 - val_loss: 14.2560 - val_mean_absolute_error: 2.9444
Epoch 264/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.6761 - mean_absolute_error: 0.8667 - val_loss: 13.2164 - val_mean_absolute_error: 2.8325
Epoch 265/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.7323 - mean_absolute_error: 0.8954 - val_loss: 14.3250 - val_mean_absolute_error: 2.7647
Epoch 266/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.0753 - mean_absolute_error: 1.0224 - val_loss: 16.0102 - val_mean_absolute_error: 3.0531
Epoch 267/1000
7/7 [==============================] - 0s 17ms/step - loss: 3.5566 - mean_absolute_error: 1.1571 - val_loss: 11.5109 - val_mean_absolute_error: 2.6468
Epoch 268/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.6104 - mean_absolute_error: 1.0778 - val_loss: 14.2485 - val_mean_absolute_error: 2.9920
Epoch 269/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.4153 - mean_absolute_error: 1.0305 - val_loss: 13.8838 - val_mean_absolute_error: 2.7478
Epoch 270/1000
7/7 [==============================] - 0s 21ms/step - loss: 2.8822 - mean_absolute_error: 1.1091 - val_loss: 14.7938 - val_mean_absolute_error: 2.9374
Epoch 271/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.1587 - mean_absolute_error: 0.9958 - val_loss: 13.1778 - val_mean_absolute_error: 2.7403
Epoch 272/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.1483 - mean_absolute_error: 0.9179 - val_loss: 13.2122 - val_mean_absolute_error: 2.7547
Epoch 273/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.2818 - mean_absolute_error: 1.0370 - val_loss: 13.6394 - val_mean_absolute_error: 2.8327
Epoch 274/1000
7/7 [==============================] - 0s 18ms/step - loss: 2.1725 - mean_absolute_error: 0.9710 - val_loss: 13.1538 - val_mean_absolute_error: 2.8590
Epoch 275/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.8247 - mean_absolute_error: 0.8524 - val_loss: 13.2541 - val_mean_absolute_error: 2.7563
Epoch 276/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.6077 - mean_absolute_error: 0.7383 - val_loss: 13.8004 - val_mean_absolute_error: 2.8290
Epoch 277/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.7312 - mean_absolute_error: 0.7981 - val_loss: 13.2351 - val_mean_absolute_error: 2.7254
Epoch 278/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.6136 - mean_absolute_error: 0.7733 - val_loss: 13.3115 - val_mean_absolute_error: 2.8249
Epoch 279/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.6583 - mean_absolute_error: 0.7662 - val_loss: 12.8859 - val_mean_absolute_error: 2.7544
Epoch 280/1000
7/7 [==============================] - 0s 26ms/step - loss: 1.5559 - mean_absolute_error: 0.7360 - val_loss: 13.7534 - val_mean_absolute_error: 2.8384
Epoch 281/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.4118 - mean_absolute_error: 0.6753 - val_loss: 13.2601 - val_mean_absolute_error: 2.7630
Epoch 282/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.4824 - mean_absolute_error: 0.6904 - val_loss: 13.5435 - val_mean_absolute_error: 2.8643
Epoch 283/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.5795 - mean_absolute_error: 0.7180 - val_loss: 13.5561 - val_mean_absolute_error: 2.7581
Epoch 284/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.4854 - mean_absolute_error: 0.7208 - val_loss: 13.6724 - val_mean_absolute_error: 2.8603
Epoch 285/1000
7/7 [==============================] - 0s 27ms/step - loss: 1.6637 - mean_absolute_error: 0.7499 - val_loss: 13.3771 - val_mean_absolute_error: 2.7196
Epoch 286/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.5863 - mean_absolute_error: 0.7491 - val_loss: 14.0570 - val_mean_absolute_error: 2.8688
Epoch 287/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.5165 - mean_absolute_error: 0.7567 - val_loss: 13.5832 - val_mean_absolute_error: 2.8444
Epoch 288/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.3690 - mean_absolute_error: 0.6916 - val_loss: 13.6316 - val_mean_absolute_error: 2.7660
Epoch 289/1000
7/7 [==============================] - 0s 32ms/step - loss: 1.5876 - mean_absolute_error: 0.7639 - val_loss: 13.9952 - val_mean_absolute_error: 2.8315
Epoch 290/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.3575 - mean_absolute_error: 0.6775 - val_loss: 14.4714 - val_mean_absolute_error: 2.9061
Epoch 291/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.3513 - mean_absolute_error: 0.6528 - val_loss: 13.5117 - val_mean_absolute_error: 2.8289
Epoch 292/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.3392 - mean_absolute_error: 0.6707 - val_loss: 13.5360 - val_mean_absolute_error: 2.8021
Epoch 293/1000
7/7 [==============================] - 0s 24ms/step - loss: 1.3690 - mean_absolute_error: 0.6694 - val_loss: 13.8520 - val_mean_absolute_error: 2.8993
Epoch 294/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.2582 - mean_absolute_error: 0.6603 - val_loss: 13.0918 - val_mean_absolute_error: 2.7356
Epoch 295/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.2206 - mean_absolute_error: 0.6054 - val_loss: 13.8794 - val_mean_absolute_error: 2.8254
Epoch 296/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.2389 - mean_absolute_error: 0.6221 - val_loss: 13.6853 - val_mean_absolute_error: 2.7977
Epoch 297/1000
7/7 [==============================] - 0s 24ms/step - loss: 1.2270 - mean_absolute_error: 0.6087 - val_loss: 13.8615 - val_mean_absolute_error: 2.8586
Epoch 298/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.2495 - mean_absolute_error: 0.5869 - val_loss: 14.5329 - val_mean_absolute_error: 2.9059
Epoch 299/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1675 - mean_absolute_error: 0.5855 - val_loss: 13.6526 - val_mean_absolute_error: 2.7747
Epoch 300/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1377 - mean_absolute_error: 0.5649 - val_loss: 13.3976 - val_mean_absolute_error: 2.7875
Epoch 301/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1762 - mean_absolute_error: 0.5837 - val_loss: 14.3869 - val_mean_absolute_error: 2.8643
Epoch 302/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.0932 - mean_absolute_error: 0.5927 - val_loss: 14.1630 - val_mean_absolute_error: 2.8814
Epoch 303/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1893 - mean_absolute_error: 0.5958 - val_loss: 14.1726 - val_mean_absolute_error: 2.8324
Epoch 304/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1309 - mean_absolute_error: 0.5640 - val_loss: 14.2133 - val_mean_absolute_error: 2.8910
Epoch 305/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.0972 - mean_absolute_error: 0.5422 - val_loss: 14.0653 - val_mean_absolute_error: 2.8691
Epoch 306/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.0617 - mean_absolute_error: 0.5565 - val_loss: 13.6935 - val_mean_absolute_error: 2.7799
Epoch 307/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0307 - mean_absolute_error: 0.5328 - val_loss: 14.3209 - val_mean_absolute_error: 2.8879
Epoch 308/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.0901 - mean_absolute_error: 0.5722 - val_loss: 13.7748 - val_mean_absolute_error: 2.8257
Epoch 309/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.2835 - mean_absolute_error: 0.6110 - val_loss: 14.4872 - val_mean_absolute_error: 2.8737
Epoch 310/1000
7/7 [==============================] - 0s 25ms/step - loss: 1.0164 - mean_absolute_error: 0.5330 - val_loss: 13.7061 - val_mean_absolute_error: 2.7780
Epoch 311/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1341 - mean_absolute_error: 0.5895 - val_loss: 13.3623 - val_mean_absolute_error: 2.8006
Epoch 312/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1567 - mean_absolute_error: 0.5836 - val_loss: 13.3512 - val_mean_absolute_error: 2.7428
Epoch 313/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1698 - mean_absolute_error: 0.6427 - val_loss: 13.8873 - val_mean_absolute_error: 2.8497
Epoch 314/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.4565 - mean_absolute_error: 0.7274 - val_loss: 14.5224 - val_mean_absolute_error: 2.8855
Epoch 315/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.1561 - mean_absolute_error: 0.6642 - val_loss: 12.9108 - val_mean_absolute_error: 2.6909
Epoch 316/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.0418 - mean_absolute_error: 0.5985 - val_loss: 14.6673 - val_mean_absolute_error: 2.9015
Epoch 317/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0734 - mean_absolute_error: 0.5988 - val_loss: 13.3070 - val_mean_absolute_error: 2.7304
Epoch 318/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.6485 - mean_absolute_error: 0.6775 - val_loss: 13.6793 - val_mean_absolute_error: 2.7573
Epoch 319/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1262 - mean_absolute_error: 0.6671 - val_loss: 14.6938 - val_mean_absolute_error: 2.8498
Epoch 320/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.2025 - mean_absolute_error: 0.6358 - val_loss: 14.1733 - val_mean_absolute_error: 2.7786
Epoch 321/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0948 - mean_absolute_error: 0.6086 - val_loss: 13.8149 - val_mean_absolute_error: 2.7760
Epoch 322/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.1640 - mean_absolute_error: 0.6445 - val_loss: 13.4273 - val_mean_absolute_error: 2.7303
Epoch 323/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.1258 - mean_absolute_error: 0.6282 - val_loss: 14.5609 - val_mean_absolute_error: 2.9034
Epoch 324/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.2281 - mean_absolute_error: 0.6214 - val_loss: 14.9671 - val_mean_absolute_error: 2.9621
Epoch 325/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1043 - mean_absolute_error: 0.6411 - val_loss: 12.9822 - val_mean_absolute_error: 2.7748
Epoch 326/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.1135 - mean_absolute_error: 0.6227 - val_loss: 14.2214 - val_mean_absolute_error: 2.8782
Epoch 327/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.3097 - mean_absolute_error: 0.6383 - val_loss: 14.1472 - val_mean_absolute_error: 2.8138
Epoch 328/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.9387 - mean_absolute_error: 0.5789 - val_loss: 13.5660 - val_mean_absolute_error: 2.7810
Epoch 329/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9973 - mean_absolute_error: 0.5558 - val_loss: 14.4357 - val_mean_absolute_error: 2.8575
Epoch 330/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.9097 - mean_absolute_error: 0.5186 - val_loss: 13.9119 - val_mean_absolute_error: 2.7797
Epoch 331/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.8871 - mean_absolute_error: 0.4846 - val_loss: 14.3041 - val_mean_absolute_error: 2.8321
Epoch 332/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.8018 - mean_absolute_error: 0.4913 - val_loss: 13.4298 - val_mean_absolute_error: 2.7844
Epoch 333/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8976 - mean_absolute_error: 0.5079 - val_loss: 14.3412 - val_mean_absolute_error: 2.8235
Epoch 334/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.9134 - mean_absolute_error: 0.5331 - val_loss: 13.6470 - val_mean_absolute_error: 2.7424
Epoch 335/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.9037 - mean_absolute_error: 0.5455 - val_loss: 14.7919 - val_mean_absolute_error: 2.8647
Epoch 336/1000
7/7 [==============================] - 0s 25ms/step - loss: 1.0885 - mean_absolute_error: 0.6295 - val_loss: 12.9366 - val_mean_absolute_error: 2.6790
Epoch 337/1000
7/7 [==============================] - 0s 31ms/step - loss: 1.4299 - mean_absolute_error: 0.7251 - val_loss: 13.5096 - val_mean_absolute_error: 2.7907
Epoch 338/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.7901 - mean_absolute_error: 0.6984 - val_loss: 15.7702 - val_mean_absolute_error: 3.0417
Epoch 339/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.8892 - mean_absolute_error: 0.8307 - val_loss: 9.7160 - val_mean_absolute_error: 2.4850
Epoch 340/1000
7/7 [==============================] - 0s 21ms/step - loss: 3.0530 - mean_absolute_error: 1.0353 - val_loss: 11.6891 - val_mean_absolute_error: 2.6125
Epoch 341/1000
7/7 [==============================] - 0s 19ms/step - loss: 2.4976 - mean_absolute_error: 0.9743 - val_loss: 14.7312 - val_mean_absolute_error: 2.8207
Epoch 342/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.3126 - mean_absolute_error: 0.9640 - val_loss: 12.3940 - val_mean_absolute_error: 2.6361
Epoch 343/1000
7/7 [==============================] - 0s 20ms/step - loss: 2.0863 - mean_absolute_error: 0.8921 - val_loss: 13.8851 - val_mean_absolute_error: 2.8386
Epoch 344/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.9182 - mean_absolute_error: 0.8678 - val_loss: 14.1725 - val_mean_absolute_error: 2.8768
Epoch 345/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.8672 - mean_absolute_error: 0.8834 - val_loss: 12.5614 - val_mean_absolute_error: 2.6982
Epoch 346/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.7687 - mean_absolute_error: 0.8474 - val_loss: 13.7631 - val_mean_absolute_error: 2.8342
Epoch 347/1000
7/7 [==============================] - 0s 33ms/step - loss: 1.5782 - mean_absolute_error: 0.7540 - val_loss: 14.6501 - val_mean_absolute_error: 2.9250
Epoch 348/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.8648 - mean_absolute_error: 0.8111 - val_loss: 13.1630 - val_mean_absolute_error: 2.7923
Epoch 349/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.7524 - mean_absolute_error: 0.7818 - val_loss: 13.9437 - val_mean_absolute_error: 2.8025
Epoch 350/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.5628 - mean_absolute_error: 0.7651 - val_loss: 14.9997 - val_mean_absolute_error: 2.9412
Epoch 351/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.5876 - mean_absolute_error: 0.7775 - val_loss: 13.0603 - val_mean_absolute_error: 2.7350
Epoch 352/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.5235 - mean_absolute_error: 0.6856 - val_loss: 14.0974 - val_mean_absolute_error: 2.8067
Epoch 353/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.5972 - mean_absolute_error: 0.7224 - val_loss: 14.2348 - val_mean_absolute_error: 2.8421
Epoch 354/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.5455 - mean_absolute_error: 0.7323 - val_loss: 13.9039 - val_mean_absolute_error: 2.9202
Epoch 355/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.8405 - mean_absolute_error: 0.8736 - val_loss: 14.0332 - val_mean_absolute_error: 2.8668
Epoch 356/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.6340 - mean_absolute_error: 0.7642 - val_loss: 15.0625 - val_mean_absolute_error: 2.9795
Epoch 357/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.5966 - mean_absolute_error: 0.7829 - val_loss: 13.4377 - val_mean_absolute_error: 2.8026
Epoch 358/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.4550 - mean_absolute_error: 0.7278 - val_loss: 14.4172 - val_mean_absolute_error: 2.9424
Epoch 359/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.5410 - mean_absolute_error: 0.7166 - val_loss: 13.7839 - val_mean_absolute_error: 2.8876
Epoch 360/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.2578 - mean_absolute_error: 0.6522 - val_loss: 13.8186 - val_mean_absolute_error: 2.8279
Epoch 361/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.2706 - mean_absolute_error: 0.6393 - val_loss: 14.2714 - val_mean_absolute_error: 2.8573
Epoch 362/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.1000 - mean_absolute_error: 0.5736 - val_loss: 15.2553 - val_mean_absolute_error: 2.9900
Epoch 363/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.1161 - mean_absolute_error: 0.5431 - val_loss: 13.2519 - val_mean_absolute_error: 2.7151
Epoch 364/1000
7/7 [==============================] - 0s 27ms/step - loss: 1.1809 - mean_absolute_error: 0.5916 - val_loss: 14.5910 - val_mean_absolute_error: 2.9089
Epoch 365/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.1678 - mean_absolute_error: 0.5615 - val_loss: 14.2992 - val_mean_absolute_error: 2.8417
Epoch 366/1000
7/7 [==============================] - 0s 25ms/step - loss: 1.3693 - mean_absolute_error: 0.6488 - val_loss: 14.1832 - val_mean_absolute_error: 2.8614
Epoch 367/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.3630 - mean_absolute_error: 0.7004 - val_loss: 14.6123 - val_mean_absolute_error: 2.9136
Epoch 368/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.1716 - mean_absolute_error: 0.6416 - val_loss: 13.8274 - val_mean_absolute_error: 2.7785
Epoch 369/1000
7/7 [==============================] - 0s 21ms/step - loss: 1.1518 - mean_absolute_error: 0.6028 - val_loss: 14.2313 - val_mean_absolute_error: 2.8424
Epoch 370/1000
7/7 [==============================] - 0s 23ms/step - loss: 1.1496 - mean_absolute_error: 0.6165 - val_loss: 14.5253 - val_mean_absolute_error: 2.8175
Epoch 371/1000
7/7 [==============================] - 0s 24ms/step - loss: 1.0095 - mean_absolute_error: 0.5228 - val_loss: 14.6922 - val_mean_absolute_error: 2.9221
Epoch 372/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9653 - mean_absolute_error: 0.5187 - val_loss: 14.4280 - val_mean_absolute_error: 2.9082
Epoch 373/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.9717 - mean_absolute_error: 0.5183 - val_loss: 14.9278 - val_mean_absolute_error: 2.9631
Epoch 374/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9388 - mean_absolute_error: 0.4895 - val_loss: 15.0855 - val_mean_absolute_error: 2.9526
Epoch 375/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0196 - mean_absolute_error: 0.4786 - val_loss: 14.2870 - val_mean_absolute_error: 2.8511
Epoch 376/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0046 - mean_absolute_error: 0.4874 - val_loss: 15.2791 - val_mean_absolute_error: 2.9519
Epoch 377/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.9403 - mean_absolute_error: 0.4750 - val_loss: 13.9751 - val_mean_absolute_error: 2.8271
Epoch 378/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9603 - mean_absolute_error: 0.4784 - val_loss: 15.4989 - val_mean_absolute_error: 3.0383
Epoch 379/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.8918 - mean_absolute_error: 0.5081 - val_loss: 14.0860 - val_mean_absolute_error: 2.7875
Epoch 380/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.8656 - mean_absolute_error: 0.5118 - val_loss: 15.3849 - val_mean_absolute_error: 2.9299
Epoch 381/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9830 - mean_absolute_error: 0.4985 - val_loss: 14.7046 - val_mean_absolute_error: 2.9066
Epoch 382/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.0010 - mean_absolute_error: 0.5209 - val_loss: 14.2985 - val_mean_absolute_error: 2.8841
Epoch 383/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.2449 - mean_absolute_error: 0.6060 - val_loss: 15.7971 - val_mean_absolute_error: 3.0291
Epoch 384/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.4486 - mean_absolute_error: 0.6038 - val_loss: 14.4146 - val_mean_absolute_error: 2.8174
Epoch 385/1000
7/7 [==============================] - 0s 18ms/step - loss: 1.1506 - mean_absolute_error: 0.5549 - val_loss: 17.5011 - val_mean_absolute_error: 3.1235
Epoch 386/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9028 - mean_absolute_error: 0.5619 - val_loss: 14.1620 - val_mean_absolute_error: 2.8164
Epoch 387/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.8405 - mean_absolute_error: 0.5670 - val_loss: 17.2370 - val_mean_absolute_error: 3.1372
7/7 [==============================] - 0s 36ms/step - loss: 0.8711 - mean_absolute_error: 0.5621 - val_loss: 13.9237 - val_mean_absolute_error: 2.8079
Epoch 389/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.8334 - mean_absolute_error: 0.5465 - val_loss: 15.3046 - val_mean_absolute_error: 2.9634
Epoch 390/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.7745 - mean_absolute_error: 0.4858 - val_loss: 14.6222 - val_mean_absolute_error: 2.8539
Epoch 391/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.8387 - mean_absolute_error: 0.5398 - val_loss: 15.5661 - val_mean_absolute_error: 2.9980
Epoch 392/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.8682 - mean_absolute_error: 0.5776 - val_loss: 13.4078 - val_mean_absolute_error: 2.7300
Epoch 393/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.9807 - mean_absolute_error: 0.5753 - val_loss: 15.1904 - val_mean_absolute_error: 2.9547
Epoch 394/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.8236 - mean_absolute_error: 0.5432 - val_loss: 15.0293 - val_mean_absolute_error: 2.9383
Epoch 395/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.8343 - mean_absolute_error: 0.5228 - val_loss: 15.5731 - val_mean_absolute_error: 2.9793
Epoch 396/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9012 - mean_absolute_error: 0.5648 - val_loss: 13.7559 - val_mean_absolute_error: 2.7668
Epoch 397/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.9442 - mean_absolute_error: 0.5642 - val_loss: 15.9267 - val_mean_absolute_error: 3.0070
Epoch 398/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.9767 - mean_absolute_error: 0.6187 - val_loss: 14.3710 - val_mean_absolute_error: 2.8009
Epoch 399/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.9427 - mean_absolute_error: 0.5810 - val_loss: 14.9165 - val_mean_absolute_error: 3.0005
Epoch 400/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.9576 - mean_absolute_error: 0.6076 - val_loss: 15.3842 - val_mean_absolute_error: 2.9920
Epoch 401/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.7742 - mean_absolute_error: 0.5334 - val_loss: 14.9895 - val_mean_absolute_error: 2.8617
Epoch 402/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7697 - mean_absolute_error: 0.5132 - val_loss: 15.3199 - val_mean_absolute_error: 2.9568
Epoch 403/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.7158 - mean_absolute_error: 0.4772 - val_loss: 14.5511 - val_mean_absolute_error: 2.9018
Epoch 404/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6855 - mean_absolute_error: 0.4667 - val_loss: 15.7693 - val_mean_absolute_error: 2.9662
Epoch 405/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6789 - mean_absolute_error: 0.4597 - val_loss: 14.9693 - val_mean_absolute_error: 2.8708
Epoch 406/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6920 - mean_absolute_error: 0.4519 - val_loss: 15.3398 - val_mean_absolute_error: 3.0131
Epoch 407/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6803 - mean_absolute_error: 0.4661 - val_loss: 15.3237 - val_mean_absolute_error: 2.9246
Epoch 408/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.7668 - mean_absolute_error: 0.4443 - val_loss: 15.0203 - val_mean_absolute_error: 2.8517
Epoch 409/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.9748 - mean_absolute_error: 0.5845 - val_loss: 15.9970 - val_mean_absolute_error: 2.9559
Epoch 410/1000
7/7 [==============================] - 0s 16ms/step - loss: 1.2001 - mean_absolute_error: 0.5889 - val_loss: 15.0172 - val_mean_absolute_error: 2.9287
Epoch 411/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.4265 - mean_absolute_error: 0.6976 - val_loss: 14.0423 - val_mean_absolute_error: 2.8386
Epoch 412/1000
7/7 [==============================] - 0s 16ms/step - loss: 1.9102 - mean_absolute_error: 0.8116 - val_loss: 16.7284 - val_mean_absolute_error: 3.0329
Epoch 413/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.3189 - mean_absolute_error: 0.7341 - val_loss: 14.1853 - val_mean_absolute_error: 2.8097
Epoch 414/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.0416 - mean_absolute_error: 0.6753 - val_loss: 15.8384 - val_mean_absolute_error: 3.0647
Epoch 415/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.0588 - mean_absolute_error: 0.6478 - val_loss: 14.6587 - val_mean_absolute_error: 2.8292
Epoch 416/1000
7/7 [==============================] - 0s 16ms/step - loss: 1.3457 - mean_absolute_error: 0.6287 - val_loss: 13.4390 - val_mean_absolute_error: 2.7722
Epoch 417/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.9473 - mean_absolute_error: 0.5921 - val_loss: 15.9665 - val_mean_absolute_error: 3.0619
Epoch 418/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.8768 - mean_absolute_error: 0.5637 - val_loss: 15.7670 - val_mean_absolute_error: 2.9912
Epoch 419/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9794 - mean_absolute_error: 0.5984 - val_loss: 14.3685 - val_mean_absolute_error: 2.8979
Epoch 420/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9169 - mean_absolute_error: 0.5412 - val_loss: 16.0598 - val_mean_absolute_error: 2.9864
Epoch 421/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9223 - mean_absolute_error: 0.5522 - val_loss: 14.3250 - val_mean_absolute_error: 2.8704
Epoch 422/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6705 - mean_absolute_error: 0.4862 - val_loss: 15.5415 - val_mean_absolute_error: 2.9827
Epoch 423/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.8034 - mean_absolute_error: 0.5151 - val_loss: 15.1364 - val_mean_absolute_error: 2.8985
Epoch 424/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6107 - mean_absolute_error: 0.4381 - val_loss: 15.4609 - val_mean_absolute_error: 2.9510
Epoch 425/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.7735 - mean_absolute_error: 0.5197 - val_loss: 14.9417 - val_mean_absolute_error: 2.8779
Epoch 426/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.9562 - mean_absolute_error: 0.6041 - val_loss: 15.5725 - val_mean_absolute_error: 2.9210
Epoch 427/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.0616 - mean_absolute_error: 0.5417 - val_loss: 15.0102 - val_mean_absolute_error: 2.9142
Epoch 428/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.8280 - mean_absolute_error: 0.5314 - val_loss: 15.4087 - val_mean_absolute_error: 2.9979
Epoch 429/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7573 - mean_absolute_error: 0.5404 - val_loss: 15.1866 - val_mean_absolute_error: 2.8714
Epoch 430/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9358 - mean_absolute_error: 0.6097 - val_loss: 14.9793 - val_mean_absolute_error: 2.9341
Epoch 431/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7821 - mean_absolute_error: 0.5589 - val_loss: 15.1976 - val_mean_absolute_error: 2.9879
Epoch 432/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7155 - mean_absolute_error: 0.4600 - val_loss: 16.3737 - val_mean_absolute_error: 3.0219
Epoch 433/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7998 - mean_absolute_error: 0.5076 - val_loss: 14.9207 - val_mean_absolute_error: 2.9106
Epoch 434/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6199 - mean_absolute_error: 0.4209 - val_loss: 15.6476 - val_mean_absolute_error: 3.0001
Epoch 435/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6470 - mean_absolute_error: 0.4256 - val_loss: 15.1753 - val_mean_absolute_error: 2.8351
Epoch 436/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7205 - mean_absolute_error: 0.4108 - val_loss: 15.8780 - val_mean_absolute_error: 3.0215
Epoch 437/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6471 - mean_absolute_error: 0.4511 - val_loss: 14.6358 - val_mean_absolute_error: 2.8778
Epoch 438/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.5777 - mean_absolute_error: 0.4180 - val_loss: 15.6385 - val_mean_absolute_error: 2.9318
Epoch 439/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6925 - mean_absolute_error: 0.4356 - val_loss: 14.8558 - val_mean_absolute_error: 2.9297
Epoch 440/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.8625 - mean_absolute_error: 0.4620 - val_loss: 16.9595 - val_mean_absolute_error: 3.0932
Epoch 441/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.1451 - mean_absolute_error: 0.4683 - val_loss: 14.2107 - val_mean_absolute_error: 2.7148
Epoch 442/1000
7/7 [==============================] - 0s 15ms/step - loss: 2.1124 - mean_absolute_error: 0.6465 - val_loss: 17.6474 - val_mean_absolute_error: 3.2192
Epoch 443/1000
7/7 [==============================] - 0s 15ms/step - loss: 2.2314 - mean_absolute_error: 0.7512 - val_loss: 13.9292 - val_mean_absolute_error: 2.7540
Epoch 444/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.9228 - mean_absolute_error: 0.7925 - val_loss: 16.6153 - val_mean_absolute_error: 3.0886
Epoch 445/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.6260 - mean_absolute_error: 0.8407 - val_loss: 14.5818 - val_mean_absolute_error: 2.9542
Epoch 446/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.5509 - mean_absolute_error: 0.8222 - val_loss: 13.7326 - val_mean_absolute_error: 2.8722
Epoch 447/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.2965 - mean_absolute_error: 0.7491 - val_loss: 17.1325 - val_mean_absolute_error: 3.1158
Epoch 448/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.1965 - mean_absolute_error: 0.7062 - val_loss: 15.2254 - val_mean_absolute_error: 2.8838
Epoch 449/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9948 - mean_absolute_error: 0.6019 - val_loss: 16.0173 - val_mean_absolute_error: 3.0150
Epoch 450/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9904 - mean_absolute_error: 0.6090 - val_loss: 15.3145 - val_mean_absolute_error: 2.9215
Epoch 451/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.0100 - mean_absolute_error: 0.6155 - val_loss: 16.3909 - val_mean_absolute_error: 3.0555
Epoch 452/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9549 - mean_absolute_error: 0.5790 - val_loss: 15.1780 - val_mean_absolute_error: 2.9471
Epoch 453/1000
7/7 [==============================] - 0s 16ms/step - loss: 1.0326 - mean_absolute_error: 0.5882 - val_loss: 16.3885 - val_mean_absolute_error: 2.9892
Epoch 454/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9114 - mean_absolute_error: 0.5689 - val_loss: 15.0467 - val_mean_absolute_error: 2.8848
Epoch 455/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7953 - mean_absolute_error: 0.5291 - val_loss: 16.0357 - val_mean_absolute_error: 3.0266
Epoch 456/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.8081 - mean_absolute_error: 0.5223 - val_loss: 16.3689 - val_mean_absolute_error: 2.9534
Epoch 457/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.8731 - mean_absolute_error: 0.5669 - val_loss: 14.2829 - val_mean_absolute_error: 2.8282
Epoch 458/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.8216 - mean_absolute_error: 0.5179 - val_loss: 15.5922 - val_mean_absolute_error: 2.9529
Epoch 459/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.8714 - mean_absolute_error: 0.5749 - val_loss: 15.0020 - val_mean_absolute_error: 2.8101
Epoch 460/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.0676 - mean_absolute_error: 0.5794 - val_loss: 15.5101 - val_mean_absolute_error: 2.9504
Epoch 461/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7943 - mean_absolute_error: 0.4941 - val_loss: 15.7480 - val_mean_absolute_error: 2.9248
Epoch 462/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7099 - mean_absolute_error: 0.4637 - val_loss: 15.9321 - val_mean_absolute_error: 2.9363
Epoch 463/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7399 - mean_absolute_error: 0.4537 - val_loss: 15.0966 - val_mean_absolute_error: 2.8812
Epoch 464/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.5988 - mean_absolute_error: 0.4141 - val_loss: 15.0629 - val_mean_absolute_error: 2.9003
Epoch 465/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9512 - mean_absolute_error: 0.4819 - val_loss: 16.0684 - val_mean_absolute_error: 2.9688
Epoch 466/1000
7/7 [==============================] - 0s 15ms/step - loss: 2.3406 - mean_absolute_error: 0.8230 - val_loss: 11.3579 - val_mean_absolute_error: 2.6156
Epoch 467/1000
7/7 [==============================] - 0s 15ms/step - loss: 3.1178 - mean_absolute_error: 0.9747 - val_loss: 10.6268 - val_mean_absolute_error: 2.4585
Epoch 468/1000
7/7 [==============================] - 0s 15ms/step - loss: 3.1344 - mean_absolute_error: 1.0361 - val_loss: 12.9022 - val_mean_absolute_error: 2.7432
Epoch 469/1000
7/7 [==============================] - 0s 15ms/step - loss: 2.1830 - mean_absolute_error: 0.9516 - val_loss: 13.9407 - val_mean_absolute_error: 2.8450
Epoch 470/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.9056 - mean_absolute_error: 0.8711 - val_loss: 13.4251 - val_mean_absolute_error: 2.7595
Epoch 471/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.5775 - mean_absolute_error: 0.7880 - val_loss: 13.7000 - val_mean_absolute_error: 2.8687
Epoch 472/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.5196 - mean_absolute_error: 0.7514 - val_loss: 12.8423 - val_mean_absolute_error: 2.7563
Epoch 473/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.2614 - mean_absolute_error: 0.6469 - val_loss: 14.4744 - val_mean_absolute_error: 2.8830
Epoch 474/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.3297 - mean_absolute_error: 0.6471 - val_loss: 13.6753 - val_mean_absolute_error: 2.8258
Epoch 475/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.4173 - mean_absolute_error: 0.6172 - val_loss: 13.8698 - val_mean_absolute_error: 2.8614
Epoch 476/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.5486 - mean_absolute_error: 0.6867 - val_loss: 13.8091 - val_mean_absolute_error: 2.8272
Epoch 477/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.4181 - mean_absolute_error: 0.6256 - val_loss: 13.3685 - val_mean_absolute_error: 2.8311
Epoch 478/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.1772 - mean_absolute_error: 0.5176 - val_loss: 14.4765 - val_mean_absolute_error: 2.9311
Epoch 479/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.1213 - mean_absolute_error: 0.5108 - val_loss: 13.7554 - val_mean_absolute_error: 2.8578
Epoch 480/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.2070 - mean_absolute_error: 0.5320 - val_loss: 13.7372 - val_mean_absolute_error: 2.8270
Epoch 481/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.2335 - mean_absolute_error: 0.5308 - val_loss: 14.5503 - val_mean_absolute_error: 2.8389
Epoch 482/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.1781 - mean_absolute_error: 0.5109 - val_loss: 13.3982 - val_mean_absolute_error: 2.7599
Epoch 483/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.3095 - mean_absolute_error: 0.6084 - val_loss: 14.1845 - val_mean_absolute_error: 2.9351
Epoch 484/1000
7/7 [==============================] - 0s 16ms/step - loss: 1.2240 - mean_absolute_error: 0.5481 - val_loss: 15.0280 - val_mean_absolute_error: 2.9833
Epoch 485/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.9547 - mean_absolute_error: 0.4341 - val_loss: 13.8229 - val_mean_absolute_error: 2.7899
Epoch 486/1000
7/7 [==============================] - 0s 16ms/step - loss: 1.0015 - mean_absolute_error: 0.4841 - val_loss: 14.7414 - val_mean_absolute_error: 2.9261
Epoch 487/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.0110 - mean_absolute_error: 0.4494 - val_loss: 13.9053 - val_mean_absolute_error: 2.8072
Epoch 488/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9528 - mean_absolute_error: 0.4019 - val_loss: 14.1300 - val_mean_absolute_error: 2.8217
Epoch 489/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9068 - mean_absolute_error: 0.4038 - val_loss: 14.7281 - val_mean_absolute_error: 2.9123
Epoch 490/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.9270 - mean_absolute_error: 0.4164 - val_loss: 14.0789 - val_mean_absolute_error: 2.8263
Epoch 491/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.0017 - mean_absolute_error: 0.4627 - val_loss: 14.7807 - val_mean_absolute_error: 2.8778
Epoch 492/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.1121 - mean_absolute_error: 0.5299 - val_loss: 14.3583 - val_mean_absolute_error: 2.8710
Epoch 493/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.1945 - mean_absolute_error: 0.5431 - val_loss: 14.0176 - val_mean_absolute_error: 2.8141
Epoch 494/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.0628 - mean_absolute_error: 0.5261 - val_loss: 14.7809 - val_mean_absolute_error: 2.8787
Epoch 495/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9868 - mean_absolute_error: 0.5054 - val_loss: 14.7605 - val_mean_absolute_error: 2.8785
Epoch 496/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.8914 - mean_absolute_error: 0.4682 - val_loss: 14.7949 - val_mean_absolute_error: 2.8371
Epoch 497/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.8569 - mean_absolute_error: 0.4468 - val_loss: 14.5394 - val_mean_absolute_error: 2.8935
Epoch 498/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.8549 - mean_absolute_error: 0.4274 - val_loss: 14.6594 - val_mean_absolute_error: 2.8712
Epoch 499/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7901 - mean_absolute_error: 0.4181 - val_loss: 14.9536 - val_mean_absolute_error: 2.9095
Epoch 500/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7626 - mean_absolute_error: 0.3807 - val_loss: 14.7007 - val_mean_absolute_error: 2.8559
Epoch 501/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7584 - mean_absolute_error: 0.3879 - val_loss: 14.6191 - val_mean_absolute_error: 2.8159
Epoch 502/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.7273 - mean_absolute_error: 0.3806 - val_loss: 14.7351 - val_mean_absolute_error: 2.8804
Epoch 503/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.8014 - mean_absolute_error: 0.3901 - val_loss: 14.3114 - val_mean_absolute_error: 2.8300
Epoch 504/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7084 - mean_absolute_error: 0.3923 - val_loss: 14.9840 - val_mean_absolute_error: 2.8830
Epoch 505/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6986 - mean_absolute_error: 0.3593 - val_loss: 14.5852 - val_mean_absolute_error: 2.8709
Epoch 506/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6406 - mean_absolute_error: 0.3416 - val_loss: 14.9583 - val_mean_absolute_error: 2.9237
Epoch 507/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6541 - mean_absolute_error: 0.3718 - val_loss: 14.9956 - val_mean_absolute_error: 2.9042
Epoch 508/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6620 - mean_absolute_error: 0.3834 - val_loss: 14.5334 - val_mean_absolute_error: 2.8597
Epoch 509/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7298 - mean_absolute_error: 0.4103 - val_loss: 14.5337 - val_mean_absolute_error: 2.8548
Epoch 510/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6670 - mean_absolute_error: 0.3959 - val_loss: 15.6344 - val_mean_absolute_error: 2.9670
Epoch 511/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.8940 - mean_absolute_error: 0.4587 - val_loss: 14.8996 - val_mean_absolute_error: 2.8700
Epoch 512/1000
7/7 [==============================] - 0s 24ms/step - loss: 1.2976 - mean_absolute_error: 0.5015 - val_loss: 15.7204 - val_mean_absolute_error: 2.9513
Epoch 513/1000
7/7 [==============================] - 0s 16ms/step - loss: 1.4781 - mean_absolute_error: 0.4885 - val_loss: 15.0092 - val_mean_absolute_error: 2.8903
Epoch 514/1000
7/7 [==============================] - 0s 22ms/step - loss: 1.0398 - mean_absolute_error: 0.5481 - val_loss: 16.0997 - val_mean_absolute_error: 3.1061
Epoch 515/1000
7/7 [==============================] - 0s 16ms/step - loss: 1.0434 - mean_absolute_error: 0.5729 - val_loss: 14.9528 - val_mean_absolute_error: 2.8786
Epoch 516/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7856 - mean_absolute_error: 0.4679 - val_loss: 15.5633 - val_mean_absolute_error: 2.9829
Epoch 517/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0920 - mean_absolute_error: 0.5818 - val_loss: 14.9440 - val_mean_absolute_error: 2.9014
Epoch 518/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0739 - mean_absolute_error: 0.5398 - val_loss: 15.1940 - val_mean_absolute_error: 2.9487
Epoch 519/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.9460 - mean_absolute_error: 0.5242 - val_loss: 14.1632 - val_mean_absolute_error: 2.8628
Epoch 520/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.9734 - mean_absolute_error: 0.6007 - val_loss: 15.3601 - val_mean_absolute_error: 2.9674
Epoch 521/1000
7/7 [==============================] - 0s 19ms/step - loss: 1.0335 - mean_absolute_error: 0.6215 - val_loss: 14.7830 - val_mean_absolute_error: 2.9033
Epoch 522/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.7897 - mean_absolute_error: 0.5337 - val_loss: 14.9846 - val_mean_absolute_error: 2.9005
Epoch 523/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7990 - mean_absolute_error: 0.5478 - val_loss: 15.2219 - val_mean_absolute_error: 2.9137
Epoch 524/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7687 - mean_absolute_error: 0.5376 - val_loss: 15.2334 - val_mean_absolute_error: 2.9504
Epoch 525/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7368 - mean_absolute_error: 0.4703 - val_loss: 15.4261 - val_mean_absolute_error: 2.9754
Epoch 526/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7711 - mean_absolute_error: 0.4838 - val_loss: 14.3329 - val_mean_absolute_error: 2.8441
Epoch 527/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.6489 - mean_absolute_error: 0.4207 - val_loss: 15.9444 - val_mean_absolute_error: 2.9881
Epoch 528/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6497 - mean_absolute_error: 0.4528 - val_loss: 14.6559 - val_mean_absolute_error: 2.8803
Epoch 529/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.5628 - mean_absolute_error: 0.3903 - val_loss: 15.5840 - val_mean_absolute_error: 2.9807
Epoch 530/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.5026 - mean_absolute_error: 0.3407 - val_loss: 15.6675 - val_mean_absolute_error: 2.9721
Epoch 531/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.4840 - mean_absolute_error: 0.2928 - val_loss: 15.2509 - val_mean_absolute_error: 2.9541
Epoch 532/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.5484 - mean_absolute_error: 0.3319 - val_loss: 15.6579 - val_mean_absolute_error: 2.9639
Epoch 533/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.5740 - mean_absolute_error: 0.3693 - val_loss: 15.2545 - val_mean_absolute_error: 2.9246
Epoch 534/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.6114 - mean_absolute_error: 0.4250 - val_loss: 15.2363 - val_mean_absolute_error: 2.9638
Epoch 535/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9002 - mean_absolute_error: 0.4356 - val_loss: 16.1343 - val_mean_absolute_error: 3.0527
Epoch 536/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.9724 - mean_absolute_error: 0.5448 - val_loss: 14.6286 - val_mean_absolute_error: 2.8547
Epoch 537/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.9998 - mean_absolute_error: 0.8126 - val_loss: 17.1937 - val_mean_absolute_error: 3.1362
Epoch 538/1000
7/7 [==============================] - 0s 15ms/step - loss: 2.1139 - mean_absolute_error: 0.9005 - val_loss: 14.5021 - val_mean_absolute_error: 2.8689
Epoch 539/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.5906 - mean_absolute_error: 0.7645 - val_loss: 16.7740 - val_mean_absolute_error: 3.0583
Epoch 540/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.8182 - mean_absolute_error: 0.8288 - val_loss: 16.4494 - val_mean_absolute_error: 3.1343
Epoch 541/1000
7/7 [==============================] - 0s 15ms/step - loss: 1.7716 - mean_absolute_error: 0.8054 - val_loss: 15.8010 - val_mean_absolute_error: 2.9933
Epoch 542/1000
7/7 [==============================] - 0s 33ms/step - loss: 2.4020 - mean_absolute_error: 0.8970 - val_loss: 15.8894 - val_mean_absolute_error: 2.9666
Epoch 543/1000
7/7 [==============================] - 0s 43ms/step - loss: 2.0767 - mean_absolute_error: 0.8572 - val_loss: 16.2573 - val_mean_absolute_error: 3.0049
Epoch 544/1000
7/7 [==============================] - 0s 14ms/step - loss: 1.6128 - mean_absolute_error: 0.7692 - val_loss: 16.0778 - val_mean_absolute_error: 2.9832
Epoch 545/1000
7/7 [==============================] - 0s 14ms/step - loss: 1.4733 - mean_absolute_error: 0.6698 - val_loss: 15.9223 - val_mean_absolute_error: 3.0190
Epoch 546/1000
7/7 [==============================] - 0s 14ms/step - loss: 1.0951 - mean_absolute_error: 0.5880 - val_loss: 14.9046 - val_mean_absolute_error: 2.8850
Epoch 547/1000
7/7 [==============================] - 618s 103s/step - loss: 0.9977 - mean_absolute_error: 0.5474 - val_loss: 16.0732 - val_mean_absolute_error: 3.0123
Epoch 548/1000
7/7 [==============================] - 1s 108ms/step - loss: 0.9274 - mean_absolute_error: 0.4987 - val_loss: 15.5388 - val_mean_absolute_error: 2.9776
Epoch 549/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.8951 - mean_absolute_error: 0.4280 - val_loss: 15.4364 - val_mean_absolute_error: 2.9251
Epoch 550/1000
7/7 [==============================] - 1s 203ms/step - loss: 0.8296 - mean_absolute_error: 0.4183 - val_loss: 15.9844 - val_mean_absolute_error: 3.0083
Epoch 551/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.7458 - mean_absolute_error: 0.4062 - val_loss: 15.5481 - val_mean_absolute_error: 2.9698
Epoch 552/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.7969 - mean_absolute_error: 0.4224 - val_loss: 15.9077 - val_mean_absolute_error: 3.0126
Epoch 553/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.7677 - mean_absolute_error: 0.4298 - val_loss: 15.5542 - val_mean_absolute_error: 2.9229
Epoch 554/1000
7/7 [==============================] - 0s 38ms/step - loss: 0.8016 - mean_absolute_error: 0.4288 - val_loss: 16.1278 - val_mean_absolute_error: 3.0028
Epoch 555/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.7462 - mean_absolute_error: 0.4071 - val_loss: 15.7517 - val_mean_absolute_error: 3.0610
Epoch 556/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.8859 - mean_absolute_error: 0.4986 - val_loss: 16.6097 - val_mean_absolute_error: 3.0612
Epoch 557/1000
7/7 [==============================] - 0s 26ms/step - loss: 1.3332 - mean_absolute_error: 0.5424 - val_loss: 15.7544 - val_mean_absolute_error: 3.0092
Epoch 558/1000
7/7 [==============================] - 0s 30ms/step - loss: 1.2640 - mean_absolute_error: 0.5320 - val_loss: 16.1901 - val_mean_absolute_error: 3.0662
Epoch 559/1000
7/7 [==============================] - 0s 26ms/step - loss: 1.5046 - mean_absolute_error: 0.5573 - val_loss: 15.8182 - val_mean_absolute_error: 3.0281
Epoch 560/1000
7/7 [==============================] - 0s 36ms/step - loss: 1.4201 - mean_absolute_error: 0.5693 - val_loss: 15.5529 - val_mean_absolute_error: 2.9637
Epoch 561/1000
7/7 [==============================] - 0s 29ms/step - loss: 1.4132 - mean_absolute_error: 0.7036 - val_loss: 16.2963 - val_mean_absolute_error: 3.0333
Epoch 562/1000
7/7 [==============================] - 0s 31ms/step - loss: 1.5316 - mean_absolute_error: 0.8015 - val_loss: 16.0599 - val_mean_absolute_error: 3.0396
Epoch 563/1000
7/7 [==============================] - 0s 47ms/step - loss: 1.3171 - mean_absolute_error: 0.7551 - val_loss: 15.5025 - val_mean_absolute_error: 2.9735
Epoch 564/1000
7/7 [==============================] - 0s 29ms/step - loss: 1.0798 - mean_absolute_error: 0.6599 - val_loss: 15.9672 - val_mean_absolute_error: 2.9780
Epoch 565/1000
7/7 [==============================] - 0s 20ms/step - loss: 1.0870 - mean_absolute_error: 0.6303 - val_loss: 18.6982 - val_mean_absolute_error: 3.2819
Epoch 566/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.9594 - mean_absolute_error: 0.6023 - val_loss: 15.8502 - val_mean_absolute_error: 3.0427
Epoch 567/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.7807 - mean_absolute_error: 0.5000 - val_loss: 16.4300 - val_mean_absolute_error: 3.1396
Epoch 568/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7806 - mean_absolute_error: 0.4841 - val_loss: 15.3018 - val_mean_absolute_error: 2.9938
Epoch 569/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.6653 - mean_absolute_error: 0.4604 - val_loss: 16.5786 - val_mean_absolute_error: 3.1211
Epoch 570/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.8334 - mean_absolute_error: 0.4191 - val_loss: 15.8170 - val_mean_absolute_error: 2.9828
Epoch 571/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.7227 - mean_absolute_error: 0.3878 - val_loss: 15.8574 - val_mean_absolute_error: 3.1006
Epoch 572/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.8153 - mean_absolute_error: 0.5113 - val_loss: 15.3862 - val_mean_absolute_error: 2.9438
Epoch 573/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.8276 - mean_absolute_error: 0.4781 - val_loss: 15.6836 - val_mean_absolute_error: 2.9452
Epoch 574/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.7297 - mean_absolute_error: 0.4022 - val_loss: 15.3797 - val_mean_absolute_error: 2.9841
Epoch 575/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.8463 - mean_absolute_error: 0.4702 - val_loss: 16.7636 - val_mean_absolute_error: 3.0862
Epoch 576/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.6406 - mean_absolute_error: 0.3950 - val_loss: 15.5958 - val_mean_absolute_error: 2.9846
Epoch 577/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.6138 - mean_absolute_error: 0.3967 - val_loss: 15.8606 - val_mean_absolute_error: 3.0191
Epoch 578/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.5040 - mean_absolute_error: 0.3570 - val_loss: 16.1317 - val_mean_absolute_error: 3.0211
Epoch 579/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.5338 - mean_absolute_error: 0.3505 - val_loss: 16.1431 - val_mean_absolute_error: 3.0029
Epoch 580/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.4561 - mean_absolute_error: 0.3248 - val_loss: 16.4190 - val_mean_absolute_error: 3.0436
Epoch 581/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.6004 - mean_absolute_error: 0.3628 - val_loss: 15.8804 - val_mean_absolute_error: 2.9739
Epoch 582/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.5612 - mean_absolute_error: 0.4046 - val_loss: 16.5089 - val_mean_absolute_error: 3.0548
Epoch 583/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.4845 - mean_absolute_error: 0.3530 - val_loss: 15.7578 - val_mean_absolute_error: 3.0459
Epoch 584/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4828 - mean_absolute_error: 0.3372 - val_loss: 16.2087 - val_mean_absolute_error: 3.0055
Epoch 585/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.4999 - mean_absolute_error: 0.4299 - val_loss: 15.7633 - val_mean_absolute_error: 2.9277
Epoch 586/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.8807 - mean_absolute_error: 0.4309 - val_loss: 16.7139 - val_mean_absolute_error: 3.0945
Epoch 587/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.8684 - mean_absolute_error: 0.4664 - val_loss: 16.0883 - val_mean_absolute_error: 2.9923
Epoch 588/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.7478 - mean_absolute_error: 0.4966 - val_loss: 16.1496 - val_mean_absolute_error: 3.0287
Epoch 589/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6019 - mean_absolute_error: 0.4512 - val_loss: 15.3061 - val_mean_absolute_error: 2.9048
Epoch 590/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.6059 - mean_absolute_error: 0.3927 - val_loss: 16.6921 - val_mean_absolute_error: 3.1427
Epoch 591/1000
7/7 [==============================] - 0s 57ms/step - loss: 0.6416 - mean_absolute_error: 0.4052 - val_loss: 15.4564 - val_mean_absolute_error: 2.9845
Epoch 592/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.5132 - mean_absolute_error: 0.3344 - val_loss: 16.4897 - val_mean_absolute_error: 3.0745
Epoch 593/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.4940 - mean_absolute_error: 0.3442 - val_loss: 15.1556 - val_mean_absolute_error: 2.8639
Epoch 594/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.4860 - mean_absolute_error: 0.3514 - val_loss: 16.8204 - val_mean_absolute_error: 3.0768
Epoch 595/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4559 - mean_absolute_error: 0.3449 - val_loss: 15.3996 - val_mean_absolute_error: 2.9399
Epoch 596/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4759 - mean_absolute_error: 0.3505 - val_loss: 16.1137 - val_mean_absolute_error: 3.0020
Epoch 597/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.4496 - mean_absolute_error: 0.3296 - val_loss: 15.9588 - val_mean_absolute_error: 2.9829
Epoch 598/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.4274 - mean_absolute_error: 0.2972 - val_loss: 16.4622 - val_mean_absolute_error: 3.0562
Epoch 599/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4253 - mean_absolute_error: 0.2805 - val_loss: 16.0073 - val_mean_absolute_error: 3.0287
Epoch 600/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.4017 - mean_absolute_error: 0.3157 - val_loss: 16.1823 - val_mean_absolute_error: 3.0111
Epoch 601/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.7089 - mean_absolute_error: 0.3471 - val_loss: 16.5762 - val_mean_absolute_error: 3.0382
Epoch 602/1000
7/7 [==============================] - 0s 40ms/step - loss: 0.6398 - mean_absolute_error: 0.3344 - val_loss: 15.4044 - val_mean_absolute_error: 2.9242
Epoch 603/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.5287 - mean_absolute_error: 0.3398 - val_loss: 16.0395 - val_mean_absolute_error: 3.0294
Epoch 604/1000
7/7 [==============================] - 0s 53ms/step - loss: 0.5809 - mean_absolute_error: 0.3350 - val_loss: 15.8405 - val_mean_absolute_error: 2.9516
Epoch 605/1000
7/7 [==============================] - 0s 43ms/step - loss: 0.5109 - mean_absolute_error: 0.3259 - val_loss: 15.9867 - val_mean_absolute_error: 3.0491
Epoch 606/1000
7/7 [==============================] - 0s 37ms/step - loss: 0.5813 - mean_absolute_error: 0.3581 - val_loss: 16.0572 - val_mean_absolute_error: 2.9736
Epoch 607/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.5113 - mean_absolute_error: 0.3245 - val_loss: 16.5362 - val_mean_absolute_error: 3.0316
Epoch 608/1000
7/7 [==============================] - 0s 40ms/step - loss: 0.4953 - mean_absolute_error: 0.2910 - val_loss: 16.3770 - val_mean_absolute_error: 2.9940
Epoch 609/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4435 - mean_absolute_error: 0.3160 - val_loss: 15.6112 - val_mean_absolute_error: 2.9316
Epoch 610/1000
7/7 [==============================] - 0s 46ms/step - loss: 0.3992 - mean_absolute_error: 0.2969 - val_loss: 16.3772 - val_mean_absolute_error: 3.0149
Epoch 611/1000
7/7 [==============================] - 0s 59ms/step - loss: 0.4530 - mean_absolute_error: 0.2966 - val_loss: 16.1207 - val_mean_absolute_error: 2.9927
Epoch 612/1000
7/7 [==============================] - 0s 44ms/step - loss: 0.3642 - mean_absolute_error: 0.2787 - val_loss: 16.0564 - val_mean_absolute_error: 3.0394
Epoch 613/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.4239 - mean_absolute_error: 0.3019 - val_loss: 15.5188 - val_mean_absolute_error: 2.8891
Epoch 614/1000
7/7 [==============================] - 0s 35ms/step - loss: 0.4084 - mean_absolute_error: 0.3037 - val_loss: 16.7355 - val_mean_absolute_error: 3.0682
Epoch 615/1000
7/7 [==============================] - 0s 40ms/step - loss: 0.3818 - mean_absolute_error: 0.2884 - val_loss: 15.8237 - val_mean_absolute_error: 2.9746
Epoch 616/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3407 - mean_absolute_error: 0.2636 - val_loss: 17.0304 - val_mean_absolute_error: 3.1065
Epoch 617/1000
7/7 [==============================] - 0s 65ms/step - loss: 0.4033 - mean_absolute_error: 0.3022 - val_loss: 15.6846 - val_mean_absolute_error: 2.9389
Epoch 618/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.3377 - mean_absolute_error: 0.2727 - val_loss: 16.9566 - val_mean_absolute_error: 3.0488
Epoch 619/1000
7/7 [==============================] - 0s 44ms/step - loss: 0.3607 - mean_absolute_error: 0.2812 - val_loss: 16.0550 - val_mean_absolute_error: 2.9667
Epoch 620/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3030 - mean_absolute_error: 0.2738 - val_loss: 16.2687 - val_mean_absolute_error: 3.0193
Epoch 621/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3062 - mean_absolute_error: 0.2782 - val_loss: 16.6478 - val_mean_absolute_error: 3.0556
Epoch 622/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3541 - mean_absolute_error: 0.2668 - val_loss: 15.3291 - val_mean_absolute_error: 2.9072
Epoch 623/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3166 - mean_absolute_error: 0.2521 - val_loss: 16.5580 - val_mean_absolute_error: 3.0364
Epoch 624/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3590 - mean_absolute_error: 0.2633 - val_loss: 15.7802 - val_mean_absolute_error: 2.9623
Epoch 625/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3977 - mean_absolute_error: 0.2979 - val_loss: 16.5705 - val_mean_absolute_error: 3.0679
Epoch 626/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3142 - mean_absolute_error: 0.2991 - val_loss: 15.7088 - val_mean_absolute_error: 2.8935
Epoch 627/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.4124 - mean_absolute_error: 0.2898 - val_loss: 16.9821 - val_mean_absolute_error: 3.1216
Epoch 628/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.3223 - mean_absolute_error: 0.3083 - val_loss: 15.3845 - val_mean_absolute_error: 2.8778
Epoch 629/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.4059 - mean_absolute_error: 0.3120 - val_loss: 17.5601 - val_mean_absolute_error: 3.1572
Epoch 630/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3255 - mean_absolute_error: 0.3546 - val_loss: 15.7412 - val_mean_absolute_error: 2.9061
Epoch 631/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4521 - mean_absolute_error: 0.3216 - val_loss: 16.2159 - val_mean_absolute_error: 3.0163
Epoch 632/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.2716 - mean_absolute_error: 0.2883 - val_loss: 15.9006 - val_mean_absolute_error: 2.9695
Epoch 633/1000
7/7 [==============================] - 0s 38ms/step - loss: 0.3531 - mean_absolute_error: 0.3333 - val_loss: 16.8412 - val_mean_absolute_error: 3.1000
Epoch 634/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.3808 - mean_absolute_error: 0.3559 - val_loss: 15.5807 - val_mean_absolute_error: 2.9173
Epoch 635/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.3634 - mean_absolute_error: 0.3496 - val_loss: 17.3291 - val_mean_absolute_error: 3.1329
Epoch 636/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.2999 - mean_absolute_error: 0.3140 - val_loss: 16.1558 - val_mean_absolute_error: 2.9760
Epoch 637/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4086 - mean_absolute_error: 0.3307 - val_loss: 16.3812 - val_mean_absolute_error: 3.0174
Epoch 638/1000
7/7 [==============================] - 0s 41ms/step - loss: 1.6160 - mean_absolute_error: 0.6463 - val_loss: 16.0674 - val_mean_absolute_error: 2.9836
Epoch 639/1000
7/7 [==============================] - 0s 33ms/step - loss: 1.5610 - mean_absolute_error: 0.6488 - val_loss: 15.8495 - val_mean_absolute_error: 2.8730
Epoch 640/1000
7/7 [==============================] - 0s 31ms/step - loss: 1.1100 - mean_absolute_error: 0.6065 - val_loss: 17.3564 - val_mean_absolute_error: 3.1699
Epoch 641/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.8995 - mean_absolute_error: 0.5622 - val_loss: 15.7215 - val_mean_absolute_error: 3.0196
Epoch 642/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.7371 - mean_absolute_error: 0.4756 - val_loss: 16.4503 - val_mean_absolute_error: 3.0555
Epoch 643/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.6038 - mean_absolute_error: 0.3924 - val_loss: 16.9357 - val_mean_absolute_error: 3.0849
Epoch 644/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.5402 - mean_absolute_error: 0.3553 - val_loss: 16.5539 - val_mean_absolute_error: 3.0414
Epoch 645/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.5282 - mean_absolute_error: 0.3291 - val_loss: 16.8044 - val_mean_absolute_error: 3.0748
Epoch 646/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4732 - mean_absolute_error: 0.2978 - val_loss: 16.6528 - val_mean_absolute_error: 3.0364
Epoch 647/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.4335 - mean_absolute_error: 0.2605 - val_loss: 16.3954 - val_mean_absolute_error: 3.0577
Epoch 648/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.4560 - mean_absolute_error: 0.2878 - val_loss: 16.2824 - val_mean_absolute_error: 2.9983
Epoch 649/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.4173 - mean_absolute_error: 0.2506 - val_loss: 17.1517 - val_mean_absolute_error: 3.0843
Epoch 650/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.4159 - mean_absolute_error: 0.2389 - val_loss: 16.1132 - val_mean_absolute_error: 2.9926
Epoch 651/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5582 - mean_absolute_error: 0.2832 - val_loss: 17.4520 - val_mean_absolute_error: 3.1304
Epoch 652/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.6091 - mean_absolute_error: 0.3483 - val_loss: 15.8515 - val_mean_absolute_error: 2.9670
Epoch 653/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.5110 - mean_absolute_error: 0.3373 - val_loss: 16.9713 - val_mean_absolute_error: 3.0798
Epoch 654/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5158 - mean_absolute_error: 0.3527 - val_loss: 16.0616 - val_mean_absolute_error: 3.0027
Epoch 655/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.5769 - mean_absolute_error: 0.3714 - val_loss: 16.4518 - val_mean_absolute_error: 3.0428
Epoch 656/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5431 - mean_absolute_error: 0.3789 - val_loss: 17.8947 - val_mean_absolute_error: 3.2202
Epoch 657/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.4977 - mean_absolute_error: 0.3526 - val_loss: 15.7993 - val_mean_absolute_error: 2.9423
Epoch 658/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.4878 - mean_absolute_error: 0.3319 - val_loss: 17.5282 - val_mean_absolute_error: 3.1676
Epoch 659/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.5040 - mean_absolute_error: 0.3470 - val_loss: 16.2860 - val_mean_absolute_error: 3.0141
Epoch 660/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4730 - mean_absolute_error: 0.3215 - val_loss: 17.4033 - val_mean_absolute_error: 3.1563
Epoch 661/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4989 - mean_absolute_error: 0.3140 - val_loss: 16.1435 - val_mean_absolute_error: 2.9543
Epoch 662/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.5450 - mean_absolute_error: 0.3520 - val_loss: 17.3030 - val_mean_absolute_error: 3.1313
Epoch 663/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.5005 - mean_absolute_error: 0.3614 - val_loss: 16.4476 - val_mean_absolute_error: 2.9754
Epoch 664/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5536 - mean_absolute_error: 0.3911 - val_loss: 16.8452 - val_mean_absolute_error: 3.0761
Epoch 665/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5004 - mean_absolute_error: 0.4032 - val_loss: 16.6580 - val_mean_absolute_error: 3.0605
Epoch 666/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.6058 - mean_absolute_error: 0.4148 - val_loss: 16.1946 - val_mean_absolute_error: 3.0085
Epoch 667/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.5690 - mean_absolute_error: 0.3822 - val_loss: 17.1866 - val_mean_absolute_error: 3.1112
Epoch 668/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5219 - mean_absolute_error: 0.3809 - val_loss: 17.1408 - val_mean_absolute_error: 3.1151
Epoch 669/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5531 - mean_absolute_error: 0.3700 - val_loss: 16.8222 - val_mean_absolute_error: 3.0414
Epoch 670/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5176 - mean_absolute_error: 0.3721 - val_loss: 16.5415 - val_mean_absolute_error: 3.0416
Epoch 671/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4922 - mean_absolute_error: 0.3742 - val_loss: 17.4225 - val_mean_absolute_error: 3.1358
Epoch 672/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.5334 - mean_absolute_error: 0.3677 - val_loss: 16.4477 - val_mean_absolute_error: 3.0559
Epoch 673/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.6448 - mean_absolute_error: 0.3904 - val_loss: 16.6915 - val_mean_absolute_error: 3.0646
Epoch 674/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.5804 - mean_absolute_error: 0.3626 - val_loss: 16.9705 - val_mean_absolute_error: 3.1537
Epoch 675/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.6011 - mean_absolute_error: 0.3307 - val_loss: 16.1024 - val_mean_absolute_error: 2.9649
Epoch 676/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.5314 - mean_absolute_error: 0.3238 - val_loss: 16.9740 - val_mean_absolute_error: 3.0390
Epoch 677/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.5736 - mean_absolute_error: 0.3520 - val_loss: 15.4736 - val_mean_absolute_error: 2.9187
Epoch 678/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.5255 - mean_absolute_error: 0.3680 - val_loss: 16.8157 - val_mean_absolute_error: 3.0596
Epoch 679/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5041 - mean_absolute_error: 0.3776 - val_loss: 15.9767 - val_mean_absolute_error: 3.0014
Epoch 680/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.5133 - mean_absolute_error: 0.3468 - val_loss: 17.5915 - val_mean_absolute_error: 3.1546
Epoch 681/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4839 - mean_absolute_error: 0.3486 - val_loss: 15.6944 - val_mean_absolute_error: 2.9328
Epoch 682/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.4829 - mean_absolute_error: 0.3236 - val_loss: 17.2338 - val_mean_absolute_error: 3.1529
Epoch 683/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4178 - mean_absolute_error: 0.2891 - val_loss: 16.1402 - val_mean_absolute_error: 2.9733
Epoch 684/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.5771 - mean_absolute_error: 0.3575 - val_loss: 16.9497 - val_mean_absolute_error: 3.0705
Epoch 685/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.5679 - mean_absolute_error: 0.3453 - val_loss: 16.7647 - val_mean_absolute_error: 3.0484
Epoch 686/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4536 - mean_absolute_error: 0.2977 - val_loss: 16.9794 - val_mean_absolute_error: 3.0759
Epoch 687/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.4315 - mean_absolute_error: 0.2840 - val_loss: 16.1352 - val_mean_absolute_error: 2.9907
Epoch 688/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.6099 - mean_absolute_error: 0.3568 - val_loss: 18.0786 - val_mean_absolute_error: 3.2582
Epoch 689/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.5666 - mean_absolute_error: 0.3637 - val_loss: 16.6916 - val_mean_absolute_error: 3.0890
Epoch 690/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.5824 - mean_absolute_error: 0.3901 - val_loss: 15.9136 - val_mean_absolute_error: 2.9473
Epoch 691/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.5880 - mean_absolute_error: 0.4354 - val_loss: 18.0854 - val_mean_absolute_error: 3.1919
Epoch 692/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.5689 - mean_absolute_error: 0.4117 - val_loss: 16.7190 - val_mean_absolute_error: 3.0874
Epoch 693/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.5390 - mean_absolute_error: 0.4137 - val_loss: 16.0306 - val_mean_absolute_error: 2.9944
Epoch 694/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.4508 - mean_absolute_error: 0.3355 - val_loss: 17.3685 - val_mean_absolute_error: 3.1514
Epoch 695/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.5785 - mean_absolute_error: 0.3521 - val_loss: 16.8352 - val_mean_absolute_error: 3.1122
Epoch 696/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.9916 - mean_absolute_error: 0.5147 - val_loss: 15.7323 - val_mean_absolute_error: 2.9668
Epoch 697/1000
7/7 [==============================] - 0s 37ms/step - loss: 1.8379 - mean_absolute_error: 0.6905 - val_loss: 17.6971 - val_mean_absolute_error: 3.1176
Epoch 698/1000
7/7 [==============================] - 0s 26ms/step - loss: 1.6802 - mean_absolute_error: 0.6714 - val_loss: 16.3004 - val_mean_absolute_error: 3.0332
Epoch 699/1000
7/7 [==============================] - 0s 25ms/step - loss: 1.3780 - mean_absolute_error: 0.6129 - val_loss: 17.1458 - val_mean_absolute_error: 3.1155
Epoch 700/1000
7/7 [==============================] - 0s 28ms/step - loss: 1.2163 - mean_absolute_error: 0.5697 - val_loss: 16.4724 - val_mean_absolute_error: 3.0703
Epoch 701/1000
7/7 [==============================] - 0s 29ms/step - loss: 1.1960 - mean_absolute_error: 0.5690 - val_loss: 16.3488 - val_mean_absolute_error: 3.0343
Epoch 702/1000
7/7 [==============================] - 0s 33ms/step - loss: 1.0001 - mean_absolute_error: 0.4524 - val_loss: 16.1202 - val_mean_absolute_error: 3.0201
Epoch 703/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.9763 - mean_absolute_error: 0.4644 - val_loss: 16.7114 - val_mean_absolute_error: 3.0874
Epoch 704/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.9808 - mean_absolute_error: 0.4071 - val_loss: 16.6788 - val_mean_absolute_error: 3.0660
Epoch 705/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.9395 - mean_absolute_error: 0.3874 - val_loss: 15.9799 - val_mean_absolute_error: 3.0260
Epoch 706/1000
7/7 [==============================] - 0s 31ms/step - loss: 1.3466 - mean_absolute_error: 0.5218 - val_loss: 16.2881 - val_mean_absolute_error: 3.0621
Epoch 707/1000
7/7 [==============================] - 0s 29ms/step - loss: 1.2369 - mean_absolute_error: 0.5281 - val_loss: 16.9393 - val_mean_absolute_error: 3.0900
Epoch 708/1000
7/7 [==============================] - 0s 32ms/step - loss: 1.2027 - mean_absolute_error: 0.5122 - val_loss: 15.8885 - val_mean_absolute_error: 2.9759
Epoch 709/1000
7/7 [==============================] - 0s 33ms/step - loss: 1.1112 - mean_absolute_error: 0.4516 - val_loss: 16.2586 - val_mean_absolute_error: 2.9748
Epoch 710/1000
7/7 [==============================] - 0s 28ms/step - loss: 1.0514 - mean_absolute_error: 0.4494 - val_loss: 15.4357 - val_mean_absolute_error: 2.9397
Epoch 711/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.9812 - mean_absolute_error: 0.4155 - val_loss: 16.4119 - val_mean_absolute_error: 3.0413
Epoch 712/1000
7/7 [==============================] - 0s 28ms/step - loss: 1.0546 - mean_absolute_error: 0.4405 - val_loss: 16.8157 - val_mean_absolute_error: 3.0468
Epoch 713/1000
7/7 [==============================] - 0s 26ms/step - loss: 1.0229 - mean_absolute_error: 0.4795 - val_loss: 16.2342 - val_mean_absolute_error: 3.0161
Epoch 714/1000
7/7 [==============================] - 0s 25ms/step - loss: 1.0045 - mean_absolute_error: 0.4937 - val_loss: 16.0713 - val_mean_absolute_error: 2.9822
Epoch 715/1000
7/7 [==============================] - 0s 28ms/step - loss: 1.0539 - mean_absolute_error: 0.5074 - val_loss: 16.3334 - val_mean_absolute_error: 3.0078
Epoch 716/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.9835 - mean_absolute_error: 0.4843 - val_loss: 16.7441 - val_mean_absolute_error: 3.0437
Epoch 717/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.8583 - mean_absolute_error: 0.4418 - val_loss: 16.1023 - val_mean_absolute_error: 3.0517
Epoch 718/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.7817 - mean_absolute_error: 0.3921 - val_loss: 16.8249 - val_mean_absolute_error: 3.0787
Epoch 719/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.8434 - mean_absolute_error: 0.3788 - val_loss: 15.9378 - val_mean_absolute_error: 2.9595
Epoch 720/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.8194 - mean_absolute_error: 0.3960 - val_loss: 16.5396 - val_mean_absolute_error: 3.0612
Epoch 721/1000
7/7 [==============================] - 0s 28ms/step - loss: 1.1333 - mean_absolute_error: 0.4715 - val_loss: 16.3009 - val_mean_absolute_error: 3.0332
Epoch 722/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.9665 - mean_absolute_error: 0.4364 - val_loss: 16.5211 - val_mean_absolute_error: 3.0246
Epoch 723/1000
7/7 [==============================] - 0s 35ms/step - loss: 0.7545 - mean_absolute_error: 0.4002 - val_loss: 16.5257 - val_mean_absolute_error: 3.0138
Epoch 724/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.8540 - mean_absolute_error: 0.3838 - val_loss: 15.7953 - val_mean_absolute_error: 2.9862
Epoch 725/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.7617 - mean_absolute_error: 0.4367 - val_loss: 16.7357 - val_mean_absolute_error: 3.0778
Epoch 726/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.6886 - mean_absolute_error: 0.4044 - val_loss: 15.6004 - val_mean_absolute_error: 2.9028
Epoch 727/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.7601 - mean_absolute_error: 0.4165 - val_loss: 16.8996 - val_mean_absolute_error: 3.1201
Epoch 728/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.7503 - mean_absolute_error: 0.4878 - val_loss: 16.3479 - val_mean_absolute_error: 3.0148
Epoch 729/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.9064 - mean_absolute_error: 0.4919 - val_loss: 16.3341 - val_mean_absolute_error: 3.0204
Epoch 730/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.6362 - mean_absolute_error: 0.4194 - val_loss: 16.7590 - val_mean_absolute_error: 3.0587
Epoch 731/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.7206 - mean_absolute_error: 0.4341 - val_loss: 16.5349 - val_mean_absolute_error: 3.0610
Epoch 732/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.6255 - mean_absolute_error: 0.4262 - val_loss: 16.8572 - val_mean_absolute_error: 3.0892
Epoch 733/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.6980 - mean_absolute_error: 0.3635 - val_loss: 16.5642 - val_mean_absolute_error: 3.0812
Epoch 734/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.8403 - mean_absolute_error: 0.4411 - val_loss: 15.9799 - val_mean_absolute_error: 2.9984
Epoch 735/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.5277 - mean_absolute_error: 0.3955 - val_loss: 16.4303 - val_mean_absolute_error: 3.0200
Epoch 736/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.7420 - mean_absolute_error: 0.4320 - val_loss: 16.9356 - val_mean_absolute_error: 3.1351
Epoch 737/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.6842 - mean_absolute_error: 0.3832 - val_loss: 16.2663 - val_mean_absolute_error: 3.0252
Epoch 738/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.7802 - mean_absolute_error: 0.4358 - val_loss: 16.9242 - val_mean_absolute_error: 3.1173
Epoch 739/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.6248 - mean_absolute_error: 0.4406 - val_loss: 16.7169 - val_mean_absolute_error: 3.0534
Epoch 740/1000
7/7 [==============================] - 0s 29ms/step - loss: 1.1793 - mean_absolute_error: 0.4999 - val_loss: 16.7809 - val_mean_absolute_error: 3.0601
Epoch 741/1000
7/7 [==============================] - 0s 29ms/step - loss: 1.0582 - mean_absolute_error: 0.5440 - val_loss: 15.6572 - val_mean_absolute_error: 2.9560
Epoch 742/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.6995 - mean_absolute_error: 0.4980 - val_loss: 16.6438 - val_mean_absolute_error: 3.0480
Epoch 743/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.6461 - mean_absolute_error: 0.4275 - val_loss: 16.4059 - val_mean_absolute_error: 3.0453
Epoch 744/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5607 - mean_absolute_error: 0.3982 - val_loss: 16.0766 - val_mean_absolute_error: 2.9941
Epoch 745/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.7184 - mean_absolute_error: 0.4043 - val_loss: 17.2901 - val_mean_absolute_error: 3.1076
Epoch 746/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.9491 - mean_absolute_error: 0.4448 - val_loss: 14.6074 - val_mean_absolute_error: 2.9192
Epoch 747/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.9472 - mean_absolute_error: 0.5171 - val_loss: 18.0172 - val_mean_absolute_error: 3.1863
Epoch 748/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.6694 - mean_absolute_error: 0.4453 - val_loss: 15.0289 - val_mean_absolute_error: 2.9294
Epoch 749/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.6672 - mean_absolute_error: 0.4583 - val_loss: 18.2421 - val_mean_absolute_error: 3.1955
Epoch 750/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.5703 - mean_absolute_error: 0.4230 - val_loss: 14.9707 - val_mean_absolute_error: 2.8692
Epoch 751/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.6763 - mean_absolute_error: 0.3985 - val_loss: 16.6859 - val_mean_absolute_error: 3.1300
Epoch 752/1000
7/7 [==============================] - 0s 44ms/step - loss: 1.1284 - mean_absolute_error: 0.5240 - val_loss: 16.5353 - val_mean_absolute_error: 2.9954
Epoch 753/1000
7/7 [==============================] - 0s 25ms/step - loss: 1.4827 - mean_absolute_error: 0.5247 - val_loss: 17.0733 - val_mean_absolute_error: 3.2142
Epoch 754/1000
7/7 [==============================] - 0s 27ms/step - loss: 1.3315 - mean_absolute_error: 0.5905 - val_loss: 16.6210 - val_mean_absolute_error: 3.0680
Epoch 755/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.9816 - mean_absolute_error: 0.5332 - val_loss: 16.9183 - val_mean_absolute_error: 3.1095
Epoch 756/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.7988 - mean_absolute_error: 0.4987 - val_loss: 15.9823 - val_mean_absolute_error: 3.0394
Epoch 757/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.8253 - mean_absolute_error: 0.5266 - val_loss: 17.3986 - val_mean_absolute_error: 3.1729
Epoch 758/1000
7/7 [==============================] - 0s 28ms/step - loss: 1.4954 - mean_absolute_error: 0.6253 - val_loss: 17.4418 - val_mean_absolute_error: 3.1878
Epoch 759/1000
7/7 [==============================] - 0s 27ms/step - loss: 1.0265 - mean_absolute_error: 0.6326 - val_loss: 16.9308 - val_mean_absolute_error: 3.0650
Epoch 760/1000
7/7 [==============================] - 0s 38ms/step - loss: 0.9570 - mean_absolute_error: 0.5970 - val_loss: 18.7164 - val_mean_absolute_error: 3.2489
Epoch 761/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.8733 - mean_absolute_error: 0.6143 - val_loss: 15.3248 - val_mean_absolute_error: 2.9013
Epoch 762/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.7729 - mean_absolute_error: 0.5028 - val_loss: 18.2072 - val_mean_absolute_error: 3.2523
Epoch 763/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.6883 - mean_absolute_error: 0.4927 - val_loss: 16.1708 - val_mean_absolute_error: 3.0331
Epoch 764/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.7253 - mean_absolute_error: 0.4839 - val_loss: 17.6501 - val_mean_absolute_error: 3.2033
Epoch 765/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.4968 - mean_absolute_error: 0.3764 - val_loss: 16.7517 - val_mean_absolute_error: 3.1139
Epoch 766/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4931 - mean_absolute_error: 0.3218 - val_loss: 16.8897 - val_mean_absolute_error: 3.1356
Epoch 767/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4711 - mean_absolute_error: 0.3213 - val_loss: 17.0224 - val_mean_absolute_error: 3.1490
Epoch 768/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.4258 - mean_absolute_error: 0.2832 - val_loss: 16.6830 - val_mean_absolute_error: 3.1082
Epoch 769/1000
7/7 [==============================] - 0s 35ms/step - loss: 0.5620 - mean_absolute_error: 0.3508 - val_loss: 18.0041 - val_mean_absolute_error: 3.1736
Epoch 770/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.5856 - mean_absolute_error: 0.3848 - val_loss: 15.8264 - val_mean_absolute_error: 3.0056
Epoch 771/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.4188 - mean_absolute_error: 0.3304 - val_loss: 17.8010 - val_mean_absolute_error: 3.1862
Epoch 772/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.6991 - mean_absolute_error: 0.3743 - val_loss: 16.4545 - val_mean_absolute_error: 3.0290
Epoch 773/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.6584 - mean_absolute_error: 0.4057 - val_loss: 16.9391 - val_mean_absolute_error: 3.1670
Epoch 774/1000
7/7 [==============================] - 0s 36ms/step - loss: 0.4705 - mean_absolute_error: 0.3452 - val_loss: 18.0207 - val_mean_absolute_error: 3.1769
Epoch 775/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4461 - mean_absolute_error: 0.3352 - val_loss: 16.2401 - val_mean_absolute_error: 3.0146
Epoch 776/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.4787 - mean_absolute_error: 0.3450 - val_loss: 17.1125 - val_mean_absolute_error: 3.1299
Epoch 777/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.5596 - mean_absolute_error: 0.3588 - val_loss: 17.1446 - val_mean_absolute_error: 3.1273
Epoch 778/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4839 - mean_absolute_error: 0.3405 - val_loss: 16.1851 - val_mean_absolute_error: 3.0262
Epoch 779/1000
7/7 [==============================] - 0s 35ms/step - loss: 0.5038 - mean_absolute_error: 0.3771 - val_loss: 17.0418 - val_mean_absolute_error: 3.1356
Epoch 780/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.5021 - mean_absolute_error: 0.3980 - val_loss: 17.1561 - val_mean_absolute_error: 3.1627
Epoch 781/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.6214 - mean_absolute_error: 0.4128 - val_loss: 16.7890 - val_mean_absolute_error: 3.1269
Epoch 782/1000
7/7 [==============================] - 0s 35ms/step - loss: 0.5061 - mean_absolute_error: 0.4075 - val_loss: 17.9014 - val_mean_absolute_error: 3.2486
Epoch 783/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.4016 - mean_absolute_error: 0.3306 - val_loss: 16.0830 - val_mean_absolute_error: 2.9969
Epoch 784/1000
7/7 [==============================] - 0s 37ms/step - loss: 0.4126 - mean_absolute_error: 0.3166 - val_loss: 17.1039 - val_mean_absolute_error: 3.1498
Epoch 785/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.3586 - mean_absolute_error: 0.2944 - val_loss: 16.1029 - val_mean_absolute_error: 3.0809
Epoch 786/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3948 - mean_absolute_error: 0.3201 - val_loss: 16.5492 - val_mean_absolute_error: 3.0935
Epoch 787/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3757 - mean_absolute_error: 0.2698 - val_loss: 16.3153 - val_mean_absolute_error: 3.0209
Epoch 788/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.5008 - mean_absolute_error: 0.3295 - val_loss: 16.2075 - val_mean_absolute_error: 3.0254
Epoch 789/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6036 - mean_absolute_error: 0.3620 - val_loss: 16.9148 - val_mean_absolute_error: 3.1036
Epoch 790/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.4525 - mean_absolute_error: 0.3277 - val_loss: 17.4440 - val_mean_absolute_error: 3.1092
Epoch 791/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.8599 - mean_absolute_error: 0.4646 - val_loss: 16.0817 - val_mean_absolute_error: 2.9865
Epoch 792/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7824 - mean_absolute_error: 0.5515 - val_loss: 16.4711 - val_mean_absolute_error: 3.1184
Epoch 793/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7829 - mean_absolute_error: 0.5331 - val_loss: 17.5918 - val_mean_absolute_error: 3.1312
Epoch 794/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.5578 - mean_absolute_error: 0.4572 - val_loss: 16.9904 - val_mean_absolute_error: 3.1205
Epoch 795/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.5231 - mean_absolute_error: 0.4337 - val_loss: 15.8604 - val_mean_absolute_error: 2.9907
Epoch 796/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.4681 - mean_absolute_error: 0.3548 - val_loss: 17.2985 - val_mean_absolute_error: 3.1759
Epoch 797/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.4204 - mean_absolute_error: 0.3225 - val_loss: 16.5211 - val_mean_absolute_error: 3.0898
Epoch 798/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.3779 - mean_absolute_error: 0.2833 - val_loss: 17.3466 - val_mean_absolute_error: 3.1707
Epoch 799/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3868 - mean_absolute_error: 0.2614 - val_loss: 16.7227 - val_mean_absolute_error: 3.0478
Epoch 800/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.3639 - mean_absolute_error: 0.2647 - val_loss: 17.4529 - val_mean_absolute_error: 3.1609
Epoch 801/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3364 - mean_absolute_error: 0.2378 - val_loss: 16.8299 - val_mean_absolute_error: 3.0660
Epoch 802/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.3740 - mean_absolute_error: 0.2754 - val_loss: 16.4403 - val_mean_absolute_error: 3.0614
Epoch 803/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.3516 - mean_absolute_error: 0.2674 - val_loss: 16.6605 - val_mean_absolute_error: 3.0695
Epoch 804/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.3200 - mean_absolute_error: 0.2412 - val_loss: 17.2941 - val_mean_absolute_error: 3.2041
Epoch 805/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.2949 - mean_absolute_error: 0.2436 - val_loss: 16.4200 - val_mean_absolute_error: 3.0346
Epoch 806/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.2771 - mean_absolute_error: 0.2354 - val_loss: 16.8091 - val_mean_absolute_error: 3.0985
Epoch 807/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2908 - mean_absolute_error: 0.2107 - val_loss: 17.2948 - val_mean_absolute_error: 3.1374
Epoch 808/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2570 - mean_absolute_error: 0.2146 - val_loss: 16.7984 - val_mean_absolute_error: 3.0951
Epoch 809/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2815 - mean_absolute_error: 0.2557 - val_loss: 16.4608 - val_mean_absolute_error: 3.0856
Epoch 810/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.2441 - mean_absolute_error: 0.2372 - val_loss: 17.0109 - val_mean_absolute_error: 3.0920
Epoch 811/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.2528 - mean_absolute_error: 0.2414 - val_loss: 16.6791 - val_mean_absolute_error: 3.0484
Epoch 812/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.3624 - mean_absolute_error: 0.2585 - val_loss: 16.6394 - val_mean_absolute_error: 3.0769
Epoch 813/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.2108 - mean_absolute_error: 0.2093 - val_loss: 16.8120 - val_mean_absolute_error: 3.0673
Epoch 814/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.2831 - mean_absolute_error: 0.2000 - val_loss: 16.7010 - val_mean_absolute_error: 3.0753
Epoch 815/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.3208 - mean_absolute_error: 0.1917 - val_loss: 16.9013 - val_mean_absolute_error: 3.0792
Epoch 816/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9965 - mean_absolute_error: 0.3017 - val_loss: 16.2553 - val_mean_absolute_error: 3.0392
Epoch 817/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.9058 - mean_absolute_error: 0.4510 - val_loss: 16.6430 - val_mean_absolute_error: 3.0458
Epoch 818/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.5998 - mean_absolute_error: 0.4775 - val_loss: 16.9559 - val_mean_absolute_error: 3.0897
Epoch 819/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.6228 - mean_absolute_error: 0.4619 - val_loss: 16.7307 - val_mean_absolute_error: 3.0798
Epoch 820/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7472 - mean_absolute_error: 0.4559 - val_loss: 17.1317 - val_mean_absolute_error: 3.2089
Epoch 821/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.5031 - mean_absolute_error: 0.3836 - val_loss: 16.0880 - val_mean_absolute_error: 3.0165
Epoch 822/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.5764 - mean_absolute_error: 0.4058 - val_loss: 17.0966 - val_mean_absolute_error: 3.1829
Epoch 823/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.5318 - mean_absolute_error: 0.4251 - val_loss: 15.0629 - val_mean_absolute_error: 2.9482
Epoch 824/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.7301 - mean_absolute_error: 0.4597 - val_loss: 17.6050 - val_mean_absolute_error: 3.2588
Epoch 825/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.5157 - mean_absolute_error: 0.4089 - val_loss: 15.5387 - val_mean_absolute_error: 2.9509
Epoch 826/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.5217 - mean_absolute_error: 0.4135 - val_loss: 16.9845 - val_mean_absolute_error: 3.1379
Epoch 827/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.3994 - mean_absolute_error: 0.3506 - val_loss: 16.7572 - val_mean_absolute_error: 3.0764
Epoch 828/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.4356 - mean_absolute_error: 0.3613 - val_loss: 16.9278 - val_mean_absolute_error: 3.0986
Epoch 829/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.5090 - mean_absolute_error: 0.3223 - val_loss: 16.0309 - val_mean_absolute_error: 2.9979
Epoch 830/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.3857 - mean_absolute_error: 0.3191 - val_loss: 16.4230 - val_mean_absolute_error: 3.0529
Epoch 831/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.4877 - mean_absolute_error: 0.2820 - val_loss: 17.0495 - val_mean_absolute_error: 3.1314
Epoch 832/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.2839 - mean_absolute_error: 0.2909 - val_loss: 16.8070 - val_mean_absolute_error: 3.1102
Epoch 833/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.7239 - mean_absolute_error: 0.3802 - val_loss: 15.5443 - val_mean_absolute_error: 2.9464
Epoch 834/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.6751 - mean_absolute_error: 0.3681 - val_loss: 17.6911 - val_mean_absolute_error: 3.1742
Epoch 835/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.4862 - mean_absolute_error: 0.3463 - val_loss: 16.5282 - val_mean_absolute_error: 3.1112
Epoch 836/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.5079 - mean_absolute_error: 0.3507 - val_loss: 17.0116 - val_mean_absolute_error: 3.1619
Epoch 837/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.3725 - mean_absolute_error: 0.3457 - val_loss: 16.2711 - val_mean_absolute_error: 3.0575
Epoch 838/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.3128 - mean_absolute_error: 0.2979 - val_loss: 17.5636 - val_mean_absolute_error: 3.1698
Epoch 839/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2966 - mean_absolute_error: 0.2970 - val_loss: 16.6913 - val_mean_absolute_error: 3.0428
Epoch 840/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.4239 - mean_absolute_error: 0.3028 - val_loss: 16.9201 - val_mean_absolute_error: 3.0806
Epoch 841/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2210 - mean_absolute_error: 0.2675 - val_loss: 15.9851 - val_mean_absolute_error: 3.0192
Epoch 842/1000
7/7 [==============================] - 0s 25ms/step - loss: 1.5071 - mean_absolute_error: 0.3997 - val_loss: 15.8663 - val_mean_absolute_error: 2.9585
Epoch 843/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.8310 - mean_absolute_error: 0.4527 - val_loss: 16.1660 - val_mean_absolute_error: 2.9330
Epoch 844/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.7636 - mean_absolute_error: 0.4950 - val_loss: 15.2947 - val_mean_absolute_error: 2.9090
Epoch 845/1000
7/7 [==============================] - 0s 15ms/step - loss: 0.7324 - mean_absolute_error: 0.5235 - val_loss: 15.3219 - val_mean_absolute_error: 2.9697
Epoch 846/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.7914 - mean_absolute_error: 0.5652 - val_loss: 16.3533 - val_mean_absolute_error: 2.9886
Epoch 847/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5271 - mean_absolute_error: 0.4691 - val_loss: 16.1399 - val_mean_absolute_error: 3.0532
Epoch 848/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.5444 - mean_absolute_error: 0.4292 - val_loss: 16.9702 - val_mean_absolute_error: 3.0842
Epoch 849/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.7800 - mean_absolute_error: 0.4411 - val_loss: 16.3960 - val_mean_absolute_error: 3.0915
Epoch 850/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.4796 - mean_absolute_error: 0.4545 - val_loss: 16.7383 - val_mean_absolute_error: 3.0672
Epoch 851/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.5816 - mean_absolute_error: 0.3806 - val_loss: 16.4977 - val_mean_absolute_error: 3.0445
Epoch 852/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.5147 - mean_absolute_error: 0.3788 - val_loss: 16.2521 - val_mean_absolute_error: 3.0152
Epoch 853/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.3190 - mean_absolute_error: 0.3371 - val_loss: 17.0910 - val_mean_absolute_error: 3.0962
Epoch 854/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3305 - mean_absolute_error: 0.3061 - val_loss: 16.3433 - val_mean_absolute_error: 2.9961
Epoch 855/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.2916 - mean_absolute_error: 0.2835 - val_loss: 16.5341 - val_mean_absolute_error: 3.0874
Epoch 856/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3355 - mean_absolute_error: 0.2779 - val_loss: 16.6149 - val_mean_absolute_error: 3.0889
Epoch 857/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3433 - mean_absolute_error: 0.2807 - val_loss: 15.9765 - val_mean_absolute_error: 2.9429
Epoch 858/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.3405 - mean_absolute_error: 0.3707 - val_loss: 18.6710 - val_mean_absolute_error: 3.2536
Epoch 859/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.8690 - mean_absolute_error: 0.4332 - val_loss: 15.1244 - val_mean_absolute_error: 2.9030
Epoch 860/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.5902 - mean_absolute_error: 0.4220 - val_loss: 17.2973 - val_mean_absolute_error: 3.1553
Epoch 861/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.4689 - mean_absolute_error: 0.3984 - val_loss: 16.1512 - val_mean_absolute_error: 2.9513
Epoch 862/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.6151 - mean_absolute_error: 0.4026 - val_loss: 16.6813 - val_mean_absolute_error: 3.0648
Epoch 863/1000
7/7 [==============================] - 1s 94ms/step - loss: 0.4913 - mean_absolute_error: 0.3843 - val_loss: 15.9380 - val_mean_absolute_error: 3.0048
Epoch 864/1000
7/7 [==============================] - 1s 85ms/step - loss: 0.5042 - mean_absolute_error: 0.3966 - val_loss: 15.2635 - val_mean_absolute_error: 2.8939
Epoch 865/1000
7/7 [==============================] - 1s 93ms/step - loss: 0.5614 - mean_absolute_error: 0.3515 - val_loss: 16.4453 - val_mean_absolute_error: 3.0314
Epoch 866/1000
7/7 [==============================] - 1s 87ms/step - loss: 0.3732 - mean_absolute_error: 0.3595 - val_loss: 16.5051 - val_mean_absolute_error: 3.0874
Epoch 867/1000
7/7 [==============================] - 0s 70ms/step - loss: 0.3664 - mean_absolute_error: 0.3434 - val_loss: 16.4838 - val_mean_absolute_error: 3.0779
Epoch 868/1000
7/7 [==============================] - 0s 51ms/step - loss: 0.3500 - mean_absolute_error: 0.3513 - val_loss: 15.8274 - val_mean_absolute_error: 2.9632
Epoch 869/1000
7/7 [==============================] - 0s 38ms/step - loss: 0.3084 - mean_absolute_error: 0.3261 - val_loss: 17.0111 - val_mean_absolute_error: 3.1190
Epoch 870/1000
7/7 [==============================] - 0s 43ms/step - loss: 0.2502 - mean_absolute_error: 0.2700 - val_loss: 15.5242 - val_mean_absolute_error: 2.9217
Epoch 871/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.2310 - mean_absolute_error: 0.2368 - val_loss: 17.2143 - val_mean_absolute_error: 3.1343
Epoch 872/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.2005 - mean_absolute_error: 0.2114 - val_loss: 15.6936 - val_mean_absolute_error: 2.9704
Epoch 873/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.2151 - mean_absolute_error: 0.2082 - val_loss: 16.4437 - val_mean_absolute_error: 3.0265
Epoch 874/1000
7/7 [==============================] - 0s 62ms/step - loss: 0.3933 - mean_absolute_error: 0.2098 - val_loss: 16.1393 - val_mean_absolute_error: 3.0231
Epoch 875/1000
7/7 [==============================] - 0s 37ms/step - loss: 0.4383 - mean_absolute_error: 0.2547 - val_loss: 15.7537 - val_mean_absolute_error: 2.9705
Epoch 876/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.2515 - mean_absolute_error: 0.2373 - val_loss: 16.8670 - val_mean_absolute_error: 3.0866
Epoch 877/1000
7/7 [==============================] - 0s 43ms/step - loss: 0.2065 - mean_absolute_error: 0.2121 - val_loss: 15.8240 - val_mean_absolute_error: 2.9913
Epoch 878/1000
7/7 [==============================] - 0s 37ms/step - loss: 0.1933 - mean_absolute_error: 0.2350 - val_loss: 16.7853 - val_mean_absolute_error: 3.0979
Epoch 879/1000
7/7 [==============================] - 0s 47ms/step - loss: 0.3054 - mean_absolute_error: 0.2696 - val_loss: 15.9628 - val_mean_absolute_error: 2.9813
Epoch 880/1000
7/7 [==============================] - 0s 38ms/step - loss: 0.1365 - mean_absolute_error: 0.2062 - val_loss: 16.5022 - val_mean_absolute_error: 3.0541
Epoch 881/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.3353 - mean_absolute_error: 0.2103 - val_loss: 16.3884 - val_mean_absolute_error: 3.0380
Epoch 882/1000
7/7 [==============================] - 0s 69ms/step - loss: 0.1573 - mean_absolute_error: 0.1938 - val_loss: 16.6958 - val_mean_absolute_error: 3.0949
Epoch 883/1000
7/7 [==============================] - 0s 58ms/step - loss: 0.1611 - mean_absolute_error: 0.1913 - val_loss: 15.9188 - val_mean_absolute_error: 2.9602
Epoch 884/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.1909 - mean_absolute_error: 0.2030 - val_loss: 16.4492 - val_mean_absolute_error: 3.0514
Epoch 885/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.1323 - mean_absolute_error: 0.1847 - val_loss: 16.5603 - val_mean_absolute_error: 3.0685
Epoch 886/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.3319 - mean_absolute_error: 0.1947 - val_loss: 16.6487 - val_mean_absolute_error: 3.0438
Epoch 887/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4226 - mean_absolute_error: 0.2506 - val_loss: 16.4659 - val_mean_absolute_error: 3.0378
Epoch 888/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.1794 - mean_absolute_error: 0.2462 - val_loss: 16.5767 - val_mean_absolute_error: 3.0326
Epoch 889/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3563 - mean_absolute_error: 0.2534 - val_loss: 16.0225 - val_mean_absolute_error: 3.0028
Epoch 890/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1960 - mean_absolute_error: 0.2361 - val_loss: 16.3819 - val_mean_absolute_error: 3.0275
Epoch 891/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.3638 - mean_absolute_error: 0.2302 - val_loss: 16.0266 - val_mean_absolute_error: 2.9951
Epoch 892/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1686 - mean_absolute_error: 0.2480 - val_loss: 16.8881 - val_mean_absolute_error: 3.0900
Epoch 893/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.3208 - mean_absolute_error: 0.2726 - val_loss: 15.9799 - val_mean_absolute_error: 3.0405
Epoch 894/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1694 - mean_absolute_error: 0.2705 - val_loss: 16.3812 - val_mean_absolute_error: 3.0722
Epoch 895/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.3534 - mean_absolute_error: 0.3493 - val_loss: 15.8059 - val_mean_absolute_error: 2.9497
Epoch 896/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.3081 - mean_absolute_error: 0.3566 - val_loss: 16.1619 - val_mean_absolute_error: 3.0217
Epoch 897/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.2168 - mean_absolute_error: 0.3398 - val_loss: 16.5201 - val_mean_absolute_error: 3.0626
Epoch 898/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.1892 - mean_absolute_error: 0.2784 - val_loss: 16.0677 - val_mean_absolute_error: 3.0148
Epoch 899/1000
7/7 [==============================] - 0s 45ms/step - loss: 1.0688 - mean_absolute_error: 0.3690 - val_loss: 16.8416 - val_mean_absolute_error: 3.0986
Epoch 900/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.8176 - mean_absolute_error: 0.3550 - val_loss: 15.7028 - val_mean_absolute_error: 3.0095
Epoch 901/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.9558 - mean_absolute_error: 0.4451 - val_loss: 16.8735 - val_mean_absolute_error: 3.0871
Epoch 902/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.5490 - mean_absolute_error: 0.3741 - val_loss: 15.4904 - val_mean_absolute_error: 2.9312
Epoch 903/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.4204 - mean_absolute_error: 0.3863 - val_loss: 17.1501 - val_mean_absolute_error: 3.1252
Epoch 904/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.2899 - mean_absolute_error: 0.3155 - val_loss: 16.5139 - val_mean_absolute_error: 3.0616
Epoch 905/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.2770 - mean_absolute_error: 0.2833 - val_loss: 16.3364 - val_mean_absolute_error: 3.0633
Epoch 906/1000
7/7 [==============================] - 0s 37ms/step - loss: 0.2262 - mean_absolute_error: 0.2665 - val_loss: 16.4935 - val_mean_absolute_error: 3.0433
Epoch 907/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.2467 - mean_absolute_error: 0.2450 - val_loss: 16.2684 - val_mean_absolute_error: 3.0238
Epoch 908/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.2118 - mean_absolute_error: 0.2291 - val_loss: 16.4787 - val_mean_absolute_error: 3.0805
Epoch 909/1000
7/7 [==============================] - 0s 44ms/step - loss: 0.1541 - mean_absolute_error: 0.2118 - val_loss: 16.3358 - val_mean_absolute_error: 3.0421
Epoch 910/1000
7/7 [==============================] - 0s 40ms/step - loss: 0.2343 - mean_absolute_error: 0.2154 - val_loss: 16.5201 - val_mean_absolute_error: 3.0334
Epoch 911/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.2543 - mean_absolute_error: 0.2217 - val_loss: 16.2094 - val_mean_absolute_error: 3.0472
Epoch 912/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.2228 - mean_absolute_error: 0.2588 - val_loss: 16.4996 - val_mean_absolute_error: 3.0821
Epoch 913/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3157 - mean_absolute_error: 0.2954 - val_loss: 16.2902 - val_mean_absolute_error: 3.0306
Epoch 914/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2002 - mean_absolute_error: 0.2762 - val_loss: 17.0393 - val_mean_absolute_error: 3.0937
Epoch 915/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.3815 - mean_absolute_error: 0.3538 - val_loss: 15.6208 - val_mean_absolute_error: 2.9344
Epoch 916/1000
7/7 [==============================] - 0s 70ms/step - loss: 0.2679 - mean_absolute_error: 0.3102 - val_loss: 17.8737 - val_mean_absolute_error: 3.1886
Epoch 917/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.2368 - mean_absolute_error: 0.3151 - val_loss: 15.5624 - val_mean_absolute_error: 2.9790
Epoch 918/1000
7/7 [==============================] - 0s 35ms/step - loss: 0.2234 - mean_absolute_error: 0.2998 - val_loss: 16.7091 - val_mean_absolute_error: 3.1075
Epoch 919/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.1558 - mean_absolute_error: 0.2458 - val_loss: 16.1445 - val_mean_absolute_error: 2.9871
Epoch 920/1000
7/7 [==============================] - 0s 56ms/step - loss: 0.1602 - mean_absolute_error: 0.2474 - val_loss: 16.5360 - val_mean_absolute_error: 3.0719
Epoch 921/1000
7/7 [==============================] - 0s 42ms/step - loss: 0.1134 - mean_absolute_error: 0.1927 - val_loss: 16.5670 - val_mean_absolute_error: 3.0601
Epoch 922/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.0701 - mean_absolute_error: 0.1524 - val_loss: 17.1975 - val_mean_absolute_error: 3.1184
Epoch 923/1000
7/7 [==============================] - 0s 35ms/step - loss: 0.1046 - mean_absolute_error: 0.1638 - val_loss: 15.9177 - val_mean_absolute_error: 2.9984
Epoch 924/1000
7/7 [==============================] - 0s 36ms/step - loss: 0.2177 - mean_absolute_error: 0.2276 - val_loss: 16.9374 - val_mean_absolute_error: 3.1237
Epoch 925/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.2114 - mean_absolute_error: 0.1885 - val_loss: 16.5886 - val_mean_absolute_error: 3.0538
Epoch 926/1000
7/7 [==============================] - 0s 31ms/step - loss: 0.2525 - mean_absolute_error: 0.3162 - val_loss: 16.6724 - val_mean_absolute_error: 3.0806
Epoch 927/1000
7/7 [==============================] - 0s 30ms/step - loss: 1.8441 - mean_absolute_error: 0.4753 - val_loss: 14.9697 - val_mean_absolute_error: 2.8837
Epoch 928/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.7986 - mean_absolute_error: 0.4696 - val_loss: 17.2164 - val_mean_absolute_error: 3.1081
Epoch 929/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.8084 - mean_absolute_error: 0.4510 - val_loss: 15.3010 - val_mean_absolute_error: 2.9060
Epoch 930/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.6941 - mean_absolute_error: 0.4870 - val_loss: 15.7793 - val_mean_absolute_error: 2.9637
Epoch 931/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.5905 - mean_absolute_error: 0.4356 - val_loss: 16.1858 - val_mean_absolute_error: 3.0061
Epoch 932/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.5170 - mean_absolute_error: 0.3726 - val_loss: 15.6890 - val_mean_absolute_error: 2.9793
Epoch 933/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.4691 - mean_absolute_error: 0.3413 - val_loss: 17.2188 - val_mean_absolute_error: 3.1444
Epoch 934/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4607 - mean_absolute_error: 0.3030 - val_loss: 15.6031 - val_mean_absolute_error: 2.9255
Epoch 935/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.3966 - mean_absolute_error: 0.3156 - val_loss: 17.0126 - val_mean_absolute_error: 3.0854
Epoch 936/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.4489 - mean_absolute_error: 0.3202 - val_loss: 15.4230 - val_mean_absolute_error: 2.9044
Epoch 937/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.4496 - mean_absolute_error: 0.2685 - val_loss: 16.5447 - val_mean_absolute_error: 3.0499
Epoch 938/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.3795 - mean_absolute_error: 0.2791 - val_loss: 15.9073 - val_mean_absolute_error: 2.9345
Epoch 939/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.4032 - mean_absolute_error: 0.2740 - val_loss: 16.2865 - val_mean_absolute_error: 3.0159
Epoch 940/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.3793 - mean_absolute_error: 0.2810 - val_loss: 16.8133 - val_mean_absolute_error: 3.0707
Epoch 941/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.3859 - mean_absolute_error: 0.2764 - val_loss: 15.5632 - val_mean_absolute_error: 2.9195
Epoch 942/1000
7/7 [==============================] - 0s 28ms/step - loss: 0.4135 - mean_absolute_error: 0.2840 - val_loss: 16.2462 - val_mean_absolute_error: 3.0229
Epoch 943/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.3569 - mean_absolute_error: 0.2987 - val_loss: 16.5680 - val_mean_absolute_error: 3.0543
Epoch 944/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4217 - mean_absolute_error: 0.2946 - val_loss: 16.4220 - val_mean_absolute_error: 3.0254
Epoch 945/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.3242 - mean_absolute_error: 0.2766 - val_loss: 16.4342 - val_mean_absolute_error: 3.0446
Epoch 946/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3035 - mean_absolute_error: 0.2598 - val_loss: 15.8009 - val_mean_absolute_error: 2.9448
Epoch 947/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.3266 - mean_absolute_error: 0.2504 - val_loss: 16.7070 - val_mean_absolute_error: 3.0545
Epoch 948/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.3037 - mean_absolute_error: 0.2561 - val_loss: 16.1435 - val_mean_absolute_error: 3.0285
Epoch 949/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.3396 - mean_absolute_error: 0.2813 - val_loss: 16.5566 - val_mean_absolute_error: 3.0233
Epoch 950/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.2776 - mean_absolute_error: 0.2595 - val_loss: 16.9565 - val_mean_absolute_error: 3.1382
Epoch 951/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.3708 - mean_absolute_error: 0.2547 - val_loss: 16.3418 - val_mean_absolute_error: 3.0038
Epoch 952/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.4073 - mean_absolute_error: 0.2725 - val_loss: 16.7625 - val_mean_absolute_error: 3.0589
Epoch 953/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3007 - mean_absolute_error: 0.2776 - val_loss: 16.5890 - val_mean_absolute_error: 3.0331
Epoch 954/1000
7/7 [==============================] - 0s 46ms/step - loss: 0.3816 - mean_absolute_error: 0.2950 - val_loss: 16.4269 - val_mean_absolute_error: 3.0328
Epoch 955/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.2385 - mean_absolute_error: 0.2329 - val_loss: 15.8832 - val_mean_absolute_error: 2.9691
Epoch 956/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2999 - mean_absolute_error: 0.2521 - val_loss: 16.3888 - val_mean_absolute_error: 3.0274
Epoch 957/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.2933 - mean_absolute_error: 0.2733 - val_loss: 16.9306 - val_mean_absolute_error: 3.1205
Epoch 958/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.3004 - mean_absolute_error: 0.3369 - val_loss: 15.9031 - val_mean_absolute_error: 2.9639
Epoch 959/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3458 - mean_absolute_error: 0.3459 - val_loss: 17.7130 - val_mean_absolute_error: 3.1481
Epoch 960/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.2344 - mean_absolute_error: 0.2810 - val_loss: 15.8587 - val_mean_absolute_error: 2.9774
Epoch 961/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3959 - mean_absolute_error: 0.3015 - val_loss: 16.9763 - val_mean_absolute_error: 3.0815
Epoch 962/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.3965 - mean_absolute_error: 0.3178 - val_loss: 16.5615 - val_mean_absolute_error: 3.0415
Epoch 963/1000
7/7 [==============================] - 0s 44ms/step - loss: 0.4812 - mean_absolute_error: 0.3978 - val_loss: 15.7042 - val_mean_absolute_error: 2.9946
Epoch 964/1000
7/7 [==============================] - 0s 47ms/step - loss: 1.1333 - mean_absolute_error: 0.4753 - val_loss: 15.1434 - val_mean_absolute_error: 2.9031
Epoch 965/1000
7/7 [==============================] - 1s 100ms/step - loss: 0.8940 - mean_absolute_error: 0.5908 - val_loss: 15.6628 - val_mean_absolute_error: 2.9999
Epoch 966/1000
7/7 [==============================] - 0s 36ms/step - loss: 1.0274 - mean_absolute_error: 0.5749 - val_loss: 16.6916 - val_mean_absolute_error: 3.0562
Epoch 967/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.7871 - mean_absolute_error: 0.5942 - val_loss: 17.4787 - val_mean_absolute_error: 3.1418
Epoch 968/1000
7/7 [==============================] - 0s 32ms/step - loss: 0.9221 - mean_absolute_error: 0.6461 - val_loss: 13.8977 - val_mean_absolute_error: 2.9019
Epoch 969/1000
7/7 [==============================] - 0s 40ms/step - loss: 0.6901 - mean_absolute_error: 0.5455 - val_loss: 17.7516 - val_mean_absolute_error: 3.2281
Epoch 970/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.6825 - mean_absolute_error: 0.5035 - val_loss: 15.2090 - val_mean_absolute_error: 2.9340
Epoch 971/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.7717 - mean_absolute_error: 0.5276 - val_loss: 17.6725 - val_mean_absolute_error: 3.2706
Epoch 972/1000
7/7 [==============================] - 0s 35ms/step - loss: 0.6862 - mean_absolute_error: 0.5495 - val_loss: 14.0100 - val_mean_absolute_error: 2.8631
Epoch 973/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.6007 - mean_absolute_error: 0.4659 - val_loss: 16.3712 - val_mean_absolute_error: 3.0651
Epoch 974/1000
7/7 [==============================] - 0s 29ms/step - loss: 0.5347 - mean_absolute_error: 0.4748 - val_loss: 15.9488 - val_mean_absolute_error: 3.0015
Epoch 975/1000
7/7 [==============================] - 0s 24ms/step - loss: 0.4561 - mean_absolute_error: 0.4542 - val_loss: 16.1102 - val_mean_absolute_error: 3.0590
Epoch 976/1000
7/7 [==============================] - 0s 33ms/step - loss: 0.4151 - mean_absolute_error: 0.4083 - val_loss: 15.6106 - val_mean_absolute_error: 2.9765
Epoch 977/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.3559 - mean_absolute_error: 0.3546 - val_loss: 15.1187 - val_mean_absolute_error: 2.9351
Epoch 978/1000
7/7 [==============================] - 0s 34ms/step - loss: 0.5056 - mean_absolute_error: 0.3633 - val_loss: 15.3024 - val_mean_absolute_error: 2.9762
Epoch 979/1000
7/7 [==============================] - 0s 27ms/step - loss: 0.4641 - mean_absolute_error: 0.3032 - val_loss: 15.2888 - val_mean_absolute_error: 2.9401
Epoch 980/1000
7/7 [==============================] - 0s 21ms/step - loss: 0.3288 - mean_absolute_error: 0.3205 - val_loss: 15.5860 - val_mean_absolute_error: 3.0349
Epoch 981/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2343 - mean_absolute_error: 0.2884 - val_loss: 15.4094 - val_mean_absolute_error: 2.9619
Epoch 982/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2706 - mean_absolute_error: 0.2715 - val_loss: 15.7896 - val_mean_absolute_error: 2.9778
Epoch 983/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.2239 - mean_absolute_error: 0.2583 - val_loss: 15.2216 - val_mean_absolute_error: 2.9533
Epoch 984/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2817 - mean_absolute_error: 0.2749 - val_loss: 15.9504 - val_mean_absolute_error: 3.0332
Epoch 985/1000
7/7 [==============================] - 0s 17ms/step - loss: 0.2452 - mean_absolute_error: 0.2463 - val_loss: 15.2078 - val_mean_absolute_error: 2.9103
Epoch 986/1000
7/7 [==============================] - 0s 23ms/step - loss: 0.2031 - mean_absolute_error: 0.2434 - val_loss: 15.6695 - val_mean_absolute_error: 3.0054
Epoch 987/1000
7/7 [==============================] - 0s 25ms/step - loss: 0.1530 - mean_absolute_error: 0.2108 - val_loss: 14.9451 - val_mean_absolute_error: 2.9230
Epoch 988/1000
7/7 [==============================] - 0s 16ms/step - loss: 0.1957 - mean_absolute_error: 0.2382 - val_loss: 16.3585 - val_mean_absolute_error: 3.0289
Epoch 989/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1827 - mean_absolute_error: 0.2244 - val_loss: 15.4591 - val_mean_absolute_error: 2.9384
Epoch 990/1000
7/7 [==============================] - 0s 45ms/step - loss: 0.1796 - mean_absolute_error: 0.2207 - val_loss: 15.5358 - val_mean_absolute_error: 2.9600
Epoch 991/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.1566 - mean_absolute_error: 0.2052 - val_loss: 15.9439 - val_mean_absolute_error: 3.0195
Epoch 992/1000
7/7 [==============================] - 0s 30ms/step - loss: 0.1426 - mean_absolute_error: 0.1896 - val_loss: 15.0004 - val_mean_absolute_error: 2.9031
Epoch 993/1000
7/7 [==============================] - 0s 38ms/step - loss: 0.2500 - mean_absolute_error: 0.2430 - val_loss: 16.6894 - val_mean_absolute_error: 3.0880
Epoch 994/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1734 - mean_absolute_error: 0.2519 - val_loss: 15.3132 - val_mean_absolute_error: 2.9697
Epoch 995/1000
7/7 [==============================] - 0s 26ms/step - loss: 0.1838 - mean_absolute_error: 0.2790 - val_loss: 15.8178 - val_mean_absolute_error: 3.0270
Epoch 996/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.2270 - mean_absolute_error: 0.2889 - val_loss: 15.5242 - val_mean_absolute_error: 2.9228
Epoch 997/1000
7/7 [==============================] - 0s 22ms/step - loss: 0.1715 - mean_absolute_error: 0.2477 - val_loss: 15.9188 - val_mean_absolute_error: 3.0495
Epoch 998/1000
7/7 [==============================] - 0s 19ms/step - loss: 0.1364 - mean_absolute_error: 0.2357 - val_loss: 14.9894 - val_mean_absolute_error: 2.9027
Epoch 999/1000
7/7 [==============================] - 0s 20ms/step - loss: 0.1325 - mean_absolute_error: 0.2503 - val_loss: 17.0825 - val_mean_absolute_error: 3.0966
Epoch 1000/1000
7/7 [==============================] - 0s 18ms/step - loss: 0.1311 - mean_absolute_error: 0.2674 - val_loss: 15.2783 - val_mean_absolute_error: 2.9224
7/7 [==============================] - 1s 4ms/step
1/1 [==============================] - 0s 21ms/step
1/1 [==============================] - 0s 20ms/step

# Calculate the RMSE
rmse_lstm = sqrt(mean_squared_error(y_test_F, test_predictions_F))
print('The RMSE value of LSTM model (FORD): {:.4f}'.format(rmse_lstm))

The RMSE value of LSTM model (FORD): 3.2206

# Plot Training Observations VS Training Predictions 
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_train_F, train_predictions_F)
plt.plot(dates_train_F, y_train_F)
plt.title('LSTM: Training Actual Returns/Training Predicted Returns (FORD)', fontsize=16)
plt.legend(['FORD Training Predictions', 'FORD Training Observations'])

# Plot Testing Observations VS Testing Predictions 
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_test_F, test_predictions_F)
plt.plot(dates_test_F, y_test_F)
plt.title('LSTM: Testing Actual Returns/Testing Predicted Returns (FORD)', fontsize=16)
plt.legend(['FORD Testing Predictions', 'FORD Testing Observations'])

# General Plot (Training, Validation & testing)
figure(figsize=(20, 10), dpi=100)
plt.plot(dates_train_F, train_predictions_F)
plt.plot(dates_train_F, y_train_F)
plt.plot(dates_val_F, val_predictions_F)
plt.plot(dates_val_F, y_val_F)
plt.plot(dates_test_F, test_predictions_F)
plt.plot(dates_test_F, y_test_F)
plt.title('LSTM: General forecasting plot (FORD)', fontsize=16)
plt.legend(['FORD Training Predictions', 
            'FORD Training Observations',
            'FORD Validation Predictions', 
            'FORD Validation Observations',
            'FORD Testing Predictions', 
            'FORD Testing Observations'])

<matplotlib.legend.Legend at 0x7fa8ad581f70>

Random Forest

Deutsche Bank AG

# transform a time series dataset into a supervised learning dataset
def series_to_supervised(DBK_RET, n_in=1, n_out=1, dropnan=True):
    n_vars = 1 if type(DBK_RET) is list else DBK_RET.shape[1]
    df = DataFrame(DBK_RET)
    cols = list()
    # input sequence (t-n, ... t-1)
    for i in range(n_in, 0, -1):
        cols.append(df.shift(i))
    # forecast sequence (t, t+1, ... t+n)
    for i in range(0, n_out):
        cols.append(df.shift(-i))
    # put it all together
    agg = concat(cols, axis=1)
    # drop rows with NaN values
    if dropnan:
        agg.dropna(inplace=True)
    return agg.values

# split a univariate dataset into train/test sets
def train_test_split(DBK_RET, n_test):
    return DBK_RET[:-n_test, :], DBK_RET[-n_test:, :]

# fit an random forest model and make a one step prediction
def random_forest_forecast(train, testX):
    # transform list into array
    train = asarray(train)
    # split into input and output columns
    trainX, trainy = train[:, :-1], train[:, -1]
    # fit model
    model = RandomForestRegressor()
    model.fit(trainX, trainy)
    # make a one-step prediction
    yhat = model.predict([testX])
    return yhat[0]

# walk-forward validation for univariate data
def walk_forward_validation(DBK_RET, n_test):
    predictions = list()
    
    # split dataset
    train, test = train_test_split(DBK_RET, n_test)
    
    # seed history with training dataset
    history = [x for x in train]
    
    # step over each time-step in the test set
    for i in range(len(test)):
        
        # split test row into input and output columns
        testX, testy = test[i, :-1], test[i, -1]
        
        # fit model on history and make a prediction
        yhat = random_forest_forecast(history, testX)
        
        # store forecast in list of predictions
        predictions.append(yhat)
        
        # add actual observation to history for the next loop
        history.append(test[i])
        
        # summarize progress
        print('>expected=%.1f, predicted=%.1f' % (testy, yhat))

    # estimate prediction error
    error = mean_absolute_error(test[:, -1], predictions)
    return error, test[:, -1], predictions

# transform the time series data into supervised learning
DBK_RET_sl = series_to_supervised(DBK_RET, n_in=6)

# Forecasting & evaluation
mae, y, yhat = walk_forward_validation(DBK_RET_sl, 12)
print('MAE: %.4f' % mae)

>expected=-2.1, predicted=-0.2
>expected=-3.2, predicted=0.1
>expected=-0.2, predicted=0.1
>expected=1.4, predicted=-0.5
>expected=0.6, predicted=0.2
>expected=1.4, predicted=-0.5
>expected=-0.7, predicted=-0.2
>expected=-4.5, predicted=-0.8
>expected=1.8, predicted=0.3
>expected=2.2, predicted=-0.2
>expected=-3.0, predicted=-0.8
>expected=0.1, predicted=-0.2
MAE: 1.7133

# Calculate the RMSE
rmse_rf = sqrt(mean_squared_error(y, yhat))
print('The RMSE value of Random Forest model (DBK): {:.4f}'.format(rmse_rf))

The RMSE value of Random Forest model (DBK): 2.0383

#plot expected vs predicted
figure(figsize=(20, 7), dpi=100)
pyplot.plot(y, label='Actual returns')
pyplot.plot(yhat, label='Predicted retuns')
pyplot.legend()
plt.title('Random forest: Actual / Predicted Returns (DBK)', fontsize=16)
pyplot.show()

Bank of America Corp

# transform a time series dataset into a supervised learning dataset
def series_to_supervised(BAC_RET, n_in=1, n_out=1, dropnan=True):
    n_vars = 1 if type(BAC_RET) is list else BAC_RET.shape[1]
    df = DataFrame(BAC_RET)
    cols = list()
    # input sequence (t-n, ... t-1)
    for i in range(n_in, 0, -1):
        cols.append(df.shift(i))
    # forecast sequence (t, t+1, ... t+n)
    for i in range(0, n_out):
        cols.append(df.shift(-i))
    # put it all together
    agg = concat(cols, axis=1)
    # drop rows with NaN values
    if dropnan:
        agg.dropna(inplace=True)
    return agg.values

# split a univariate dataset into train/test sets
def train_test_split(BAC_RET, n_test):
    return BAC_RET[:-n_test, :], BAC_RET[-n_test:, :]

# fit an random forest model and make a one step prediction
def random_forest_forecast(train, testX):
    # transform list into array
    train = asarray(train)
    # split into input and output columns
    trainX, trainy = train[:, :-1], train[:, -1]
    # fit model
    model = RandomForestRegressor()
    model.fit(trainX, trainy)
    # make a one-step prediction
    yhat = model.predict([testX])
    return yhat[0]

# walk-forward validation for univariate data
def walk_forward_validation(BAC_RET, n_test):
    predictions = list()
    
    # split dataset
    train, test = train_test_split(BAC_RET, n_test)
    
    # seed history with training dataset
    history = [x for x in train]
    
    # step over each time-step in the test set
    for i in range(len(test)):
        
        # split test row into input and output columns
        testX, testy = test[i, :-1], test[i, -1]
        
        # fit model on history and make a prediction
        yhat = random_forest_forecast(history, testX)
        
        # store forecast in list of predictions
        predictions.append(yhat)
        
        # add actual observation to history for the next loop
        history.append(test[i])
        
        # summarize progress
        print('>expected=%.1f, predicted=%.1f' % (testy, yhat))

    # estimate prediction error
    error = mean_absolute_error(test[:, -1], predictions)
    return error, test[:, -1], predictions

# transform the time series data into supervised learning
BAC_RET_sl = series_to_supervised(BAC_RET, n_in=6)

# Forecasting & evaluation
mae, y, yhat = walk_forward_validation(BAC_RET_sl, 12)
print('MAE: %.4f' % mae)

>expected=1.1, predicted=-0.0
>expected=-1.9, predicted=-0.1
>expected=-1.2, predicted=0.3
>expected=1.5, predicted=-0.1
>expected=0.3, predicted=0.2
>expected=0.4, predicted=-0.2
>expected=-0.6, predicted=0.1
>expected=3.7, predicted=0.3
>expected=-1.8, predicted=-0.6
>expected=2.8, predicted=0.2
>expected=-0.4, predicted=-0.3
>expected=-0.1, predicted=-0.2
MAE: 1.2279

# Calculate the RMSE
rmse_rf = sqrt(mean_squared_error(y, yhat))
print('The RMSE value of Random Forest model (BAC): {:.4f}'.format(rmse_rf))

The RMSE value of Random Forest model (BAC): 1.5683

#plot expected vs predicted
figure(figsize=(20, 7), dpi=100)
pyplot.plot(y, label='Actual returns')
pyplot.plot(yhat, label='Predicted retuns')
pyplot.legend()
plt.title('Random forest: Actual / Predicted Returns (BAC)', fontsize=16)
pyplot.show()

BMW

# transform a time series dataset into a supervised learning dataset
def series_to_supervised(BMW_RET, n_in=1, n_out=1, dropnan=True):
    n_vars = 1 if type(BMW_RET) is list else BMW_RET.shape[1]
    df = DataFrame(BMW_RET)
    cols = list()
    # input sequence (t-n, ... t-1)
    for i in range(n_in, 0, -1):
        cols.append(df.shift(i))
    # forecast sequence (t, t+1, ... t+n)
    for i in range(0, n_out):
        cols.append(df.shift(-i))
    # put it all together
    agg = concat(cols, axis=1)
    # drop rows with NaN values
    if dropnan:
        agg.dropna(inplace=True)
    return agg.values

# split a univariate dataset into train/test sets
def train_test_split(BMW_RET, n_test):
    return BMW_RET[:-n_test, :], BMW_RET[-n_test:, :]

# fit an random forest model and make a one step prediction
def random_forest_forecast(train, testX):
    # transform list into array
    train = asarray(train)
    # split into input and output columns
    trainX, trainy = train[:, :-1], train[:, -1]
    # fit model
    model = RandomForestRegressor()
    model.fit(trainX, trainy)
    # make a one-step prediction
    yhat = model.predict([testX])
    return yhat[0]

# walk-forward validation for univariate data
def walk_forward_validation(BMW_RET, n_test):
    predictions = list()
    
    # split dataset
    train, test = train_test_split(BMW_RET, n_test)
    
    # seed history with training dataset
    history = [x for x in train]
    
    # step over each time-step in the test set
    for i in range(len(test)):
        
        # split test row into input and output columns
        testX, testy = test[i, :-1], test[i, -1]
        
        # fit model on history and make a prediction
        yhat = random_forest_forecast(history, testX)
        
        # store forecast in list of predictions
        predictions.append(yhat)
        
        # add actual observation to history for the next loop
        history.append(test[i])
        
        # summarize progress
        print('>expected=%.1f, predicted=%.1f' % (testy, yhat))

    # estimate prediction error
    error = mean_absolute_error(test[:, -1], predictions)
    return error, test[:, -1], predictions

# transform the time series data into supervised learning
BMW_RET_sl = series_to_supervised(BMW_RET, n_in=6)

# Forecasting & evaluation
mae, y, yhat = walk_forward_validation(BMW_RET_sl, 12)
print('MAE: %.4f' % mae)

>expected=-2.5, predicted=-0.0
>expected=-1.2, predicted=-0.6
>expected=2.0, predicted=0.5
>expected=2.7, predicted=0.0
>expected=0.8, predicted=-0.7
>expected=-0.9, predicted=-0.1
>expected=0.6, predicted=-0.9
>expected=-3.0, predicted=0.6
>expected=0.2, predicted=-0.5
>expected=1.8, predicted=-0.4
>expected=-0.5, predicted=-0.1
>expected=-1.3, predicted=0.1
MAE: 1.5796

# Calculate the RMSE
rmse_rf = sqrt(mean_squared_error(y, yhat))
print('The RMSE value of Random Forest model (BMW): {:.4f}'.format(rmse_rf))

The RMSE value of Random Forest model (BMW): 1.8348

#plot expected vs predicted
figure(figsize=(20, 7), dpi=100)
pyplot.plot(y, label='Actual returns')
pyplot.plot(yhat, label='Predicted retuns')
pyplot.legend()
plt.title('Random forest: Actual / Predicted Returns (BMW)', fontsize=16)
pyplot.show()

Ford

# transform a time series dataset into a supervised learning dataset
def series_to_supervised(F_RET, n_in=1, n_out=1, dropnan=True):
    n_vars = 1 if type(F_RET) is list else F_RET.shape[1]
    df = DataFrame(F_RET)
    cols = list()
    # input sequence (t-n, ... t-1)
    for i in range(n_in, 0, -1):
        cols.append(df.shift(i))
    # forecast sequence (t, t+1, ... t+n)
    for i in range(0, n_out):
        cols.append(df.shift(-i))
    # put it all together
    agg = concat(cols, axis=1)
    # drop rows with NaN values
    if dropnan:
        agg.dropna(inplace=True)
    return agg.values

# split a univariate dataset into train/test sets
def train_test_split(F_RET, n_test):
    return F_RET[:-n_test, :], F_RET[-n_test:, :]

# fit an random forest model and make a one step prediction
def random_forest_forecast(train, testX):
    # transform list into array
    train = asarray(train)
    # split into input and output columns
    trainX, trainy = train[:, :-1], train[:, -1]
    # fit model
    model = RandomForestRegressor()
    model.fit(trainX, trainy)
    # make a one-step prediction
    yhat = model.predict([testX])
    return yhat[0]

# walk-forward validation for univariate data
def walk_forward_validation(F_RET, n_test):
    predictions = list()
    
    # split dataset
    train, test = train_test_split(F_RET, n_test)
    
    # seed history with training dataset
    history = [x for x in train]
    
    # step over each time-step in the test set
    for i in range(len(test)):
        
        # split test row into input and output columns
        testX, testy = test[i, :-1], test[i, -1]
        
        # fit model on history and make a prediction
        yhat = random_forest_forecast(history, testX)
        
        # store forecast in list of predictions
        predictions.append(yhat)
        
        # add actual observation to history for the next loop
        history.append(test[i])
        
        # summarize progress
        print('>expected=%.1f, predicted=%.1f' % (testy, yhat))

    # estimate prediction error
    error = mean_absolute_error(test[:, -1], predictions)
    return error, test[:, -1], predictions

# transform the time series data into supervised learning
F_RET_sl = series_to_supervised(F_RET, n_in=6)

# Forecasting & evaluation
mae, y, yhat = walk_forward_validation(F_RET_sl, 12)
print('MAE: %.4f' % mae)

>expected=-3.6, predicted=-0.9
>expected=-1.1, predicted=-0.6
>expected=-1.2, predicted=-0.7
>expected=2.7, predicted=-0.6
>expected=-1.2, predicted=-0.2
>expected=0.4, predicted=-0.2
>expected=-1.4, predicted=-0.2
>expected=-0.2, predicted=-0.2
>expected=-1.6, predicted=0.2
>expected=2.2, predicted=-0.4
>expected=-0.8, predicted=-0.3
>expected=0.5, predicted=0.2
MAE: 1.2592

# Calculate the RMSE
rmse_rf = sqrt(mean_squared_error(y, yhat))
print('The RMSE value of Random Forest model (FORD): {:.4f}'.format(rmse_rf))

The RMSE value of Random Forest model (FORD): 1.6323

#plot expected vs predicted
figure(figsize=(20, 7), dpi=100)
pyplot.plot(y, label='Actual returns')
pyplot.plot(yhat, label='Predicted retuns')
pyplot.legend()
plt.title('Random forest: Actual / Predicted Returns (FORD)', fontsize=16)
pyplot.show()

Models comparison

# Compare the RMSE of the models

## create data
data_RMSE = [["ARCH", 0.2504,0.2273, 0.2005 ,0.2219 ], 
             ["GARCH", 0.2076,0.1982, 0.1828 , 0.2174], 
             ["GARCH-t", 0.2074,0.2018, 0.1860 , 0.2236], 
             ["EGARCH", 0.2161,0.1997, 0.1836 , 0.2243], 
             ["GJR-GARCH", 0.2072,0.1787, 0.1722 , 0.2156],
             ["LSTM", 2.6075 ,1.8953, 2.5942 , 3.2206], 
             ["Random Forest", 2.0383,1.5683, 1.8348 , 1.6323]
            ]
  
## define header names
col_names = ["Models", "RMSE_DBK","RMSE_BAC", "RMSE_BMW", "RMSE_FORD"]
  
## display table
print(tabulate(data_RMSE, headers=col_names, tablefmt="fancy_grid"))

╒═══════════════╤════════════╤════════════╤════════════╤═════════════╕
│ Models        │   RMSE_DBK │   RMSE_BAC │   RMSE_BMW │   RMSE_FORD │
╞═══════════════╪════════════╪════════════╪════════════╪═════════════╡
│ ARCH          │     0.2504 │     0.2273 │     0.2005 │      0.2219 │
├───────────────┼────────────┼────────────┼────────────┼─────────────┤
│ GARCH         │     0.2076 │     0.1982 │     0.1828 │      0.2174 │
├───────────────┼────────────┼────────────┼────────────┼─────────────┤
│ GARCH-t       │     0.2074 │     0.2018 │     0.186  │      0.2236 │
├───────────────┼────────────┼────────────┼────────────┼─────────────┤
│ EGARCH        │     0.2161 │     0.1997 │     0.1836 │      0.2243 │
├───────────────┼────────────┼────────────┼────────────┼─────────────┤
│ GJR-GARCH     │     0.2072 │     0.1787 │     0.1722 │      0.2156 │
├───────────────┼────────────┼────────────┼────────────┼─────────────┤
│ LSTM          │     2.6075 │     1.8953 │     2.5942 │      3.2206 │
├───────────────┼────────────┼────────────┼────────────┼─────────────┤
│ Random Forest │     2.0383 │     1.5683 │     1.8348 │      1.6323 │
╘═══════════════╧════════════╧════════════╧════════════╧═════════════╛

For each company, we designed and applied GARCH, LTSM, and Random Forest models to demonstrate their importance in forecasting the volatility of these markets. Based on the forecasting results obtained, we can conclude that GARCH models performed much better than Data Science models. Indeed, the best model performance was from GJR GARCH by giving the lowest RMSE and LSTM had the worst performance in both industries.